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

    Neuronpedia

    INDEX
    Explanations

    terms related to matrix operations and their impact in mathematical contexts

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

    Letters and asterisks followed by other letters or numbers

    np_acts-logits-general · gemini-2.0-flash

    wild type and mutant genes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     myſelf
    -1.07
     itſelf
    -0.98
     themſelves
    -0.95
     pleaſure
    -0.95
     purpoſe
    -0.94
     himſelf
    -0.93
     houſe
    -0.91
     crdi
    -0.90
     deſt
    -0.89
     raiſ
    -0.89
    POSITIVE LOGITS
     m
    0.75
     z
    0.73
     q
    0.70
     c
    0.69
     d
    0.67
     r
    0.65
     k
    0.65
     n
    0.65
     p
    0.63
     x
    0.62
    Act Density 1.329%

    No Known Activations