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

    Neuronpedia

    INDEX
    Explanations

    terms related to the publishing process

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

    Text followed by publication dates

    np_acts-logits-general · gemini-2.0-flash

    publication date

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    NameInMap
    -0.59
    top
    -0.58
    EndContext
    -0.56
     Z
    -0.53
    noks
    -0.53
    IContainer
    -0.52
     
    -0.52
    zor
    -0.51
     cintura
    -0.51
     z
    -0.50
    POSITIVE LOGITS
     houſe
    0.88
    .}~\
    0.86
    inghouse
    0.85
    quelize
    0.84
     myſelf
    0.82
     Theſe
    0.82
    にほんブログ村
    0.80
    )");
    0.79
    )*/
    0.79
     raiſ
    0.78
    Act Density 0.076%

    No Known Activations