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

    Neuronpedia

    INDEX
    Explanations

    numeric values and identifiers in technical or scientific contexts

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

    Numerical sequences or IDs

    np_acts-logits-general · gemini-2.0-flash

    numbers and related punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Efq
    -1.36
    ſelf
    -1.23
     myſelf
    -1.18
     Monfieur
    -1.17
     houſe
    -1.15
     leaſt
    -1.15
     Theſe
    -1.14
     raiſ
    -1.12
     itſelf
    -1.10
     himſelf
    -1.09
    POSITIVE LOGITS
    3
    0.64
    4
    0.63
    2
    0.63
    1
    0.62
    6
    0.60
    0
    0.59
    5
    0.59
    8
    0.58
    9
    0.58
    7
    0.58
    Act Density 1.353%

    No Known Activations