Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    terms and concepts related to statistical distributions and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Mathematical probability and distributions

    np_acts-logits-general · gemini-2.0-flash

    probability distributions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    BlockPos
    -0.59
    ########.
    -0.52
     bezeichneter
    -0.52
     Roskov
    -0.51
     onOptions
    -0.48
    fieldId
    -0.47
     صوتيه
    -0.47
    hyrchwyd
    -0.46
     Phenomen
    -0.43
     gua
    -0.43
    POSITIVE LOGITS
     distribution
    1.14
     probability
    1.14
     distributions
    1.06
     Distribution
    1.05
     probabilities
    1.00
     Probability
    0.98
    Distribution
    0.98
    distribution
    0.97
    probability
    0.92
    Probability
    0.91
    Act Density 2.119%

    No Known Activations