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

    Neuronpedia

    INDEX
    Explanations

    indicators of code documentation and comments

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

    user turn begins

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.84
    RenderAtEndOf
    -0.71
    awtextra
    -0.68
    новниш
    -0.59
    COUVER
    -0.59
    новништво
    -0.56
    EndInit
    -0.54
     <<<<<<<<<<<<<<
    -0.54
    principalColumn
    -0.53
     utafitiHapana
    -0.53
    POSITIVE LOGITS
    хьтан
    0.51
    IContainer
    0.47
     StatefulWidget
    0.40
     carreira
    0.38
    ///
    0.35
     critères
    0.34
    /';
    0.33
     JADX
    0.32
     amistad
    0.32
     Sava
    0.32
    Act Density 0.000%

    No Known Activations