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

    Neuronpedia

    INDEX
    Explanations

    references to statistical methods and their applications in research

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

    Comes after periods and quotation marks

    np_acts-logits-general · gemini-2.0-flash

    case names and citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     myſelf
    -1.25
     itſelf
    -1.21
     themſelves
    -1.14
     Jefus
    -0.98
     himſelf
    -0.98
    ^(@)
    -0.97
     purpoſe
    -0.91
     uſed
    -0.91
     houſe
    -0.89
     quelcon
    -0.89
    POSITIVE LOGITS
    ագրություններ
    0.78
    ${\
    0.73
    kl
    0.71
    +"
    0.70
    kle
    0.69
    df
    0.69
    sem
    0.67
    ni
    0.67
    Ve
    0.66
    blo
    0.66
    Act Density 0.868%

    No Known Activations