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

    Neuronpedia

    INDEX
    Explanations

    effects

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     благодаря
    -0.07
     آموز
    -0.06
    �
    -0.06
    cur
    -0.06
    (rt
    -0.06
    スタ
    -0.06
     trailers
    -0.06
    िन
    -0.06
    依
    -0.06
    ㅋㅋㅋㅋ
    -0.06
    POSITIVE LOGITS
    _DM
    0.06
    
    0.06
     другим
    0.06
     цик
    0.06
    ’↵↵
    0.06
     setType
    0.06
     ø
    0.06
     چین
    0.06
    pitch
    0.06
    _ASSIGN
    0.06
    Act Density 0.239%

    No Known Activations