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

    Neuronpedia

    INDEX
    Explanations

    segments of text that demonstrate formatting or indentation style

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

    code declarations and keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     "..\..\..\
    -0.74
     "..\..\
    -0.68
    ValueStyle
    -0.57
    ロウィン
    -0.55
     ब्रेकडाउन
    -0.54
     MainAxisSize
    -0.52
    ropriate
    -0.51
    niſſe
    -0.50
     increí
    -0.50
    Jeografia
    -0.50
    POSITIVE LOGITS
     defStyleAttr
    0.34
    QPushButton
    0.33
    function
    0.31
    تری
    0.31
     hơi
    0.31
     
    0.30
     
    0.30
     التن
    0.30
     zahr
    0.30
     StatefulWidget
    0.30
    Act Density 0.022%

    No Known Activations