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

    Neuronpedia

    INDEX
    Explanations

    references to specific individual names or mentions within a text

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

    names followed by specific surnames

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Gies
    -0.32
     pux
    -0.28
     meeste
    -0.28
    apimachinery
    -0.28
     خوب
    -0.28
     phục
    -0.27
     spezial
    -0.27
     comprehend
    -0.27
    ơi
    -0.26
    //
    -0.26
    POSITIVE LOGITS
    MessageOf
    0.67
     للاسماء
    0.62
    DockStyle
    0.59
    LookAnd
    0.58
     myſelf
    0.57
     ſch
    0.56
     Undeclared
    0.54
     initComponents
    0.54
    Sens
    0.53
    AndroidJUnit
    0.53
    Act Density 0.027%

    No Known Activations