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

    Neuronpedia

    INDEX
    Explanations

    content type and charset

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     واکنش
    0.42
     copol
    0.41
    льным
    0.40
    メートル
    0.38
     prévoit
    0.38
     RESPONSE
    0.38
     TUM
    0.38
    当作
    0.38
     لو
    0.38
    onnaise
    0.38
    POSITIVE LOGITS
    ;
    0.81
    charset
    0.63
    ;",
    0.54
    ;"
    0.52
    ;.
    0.52
    ;}
    0.49
    ;/
    0.48
     Char
    0.48
    ;<
    0.48
    ;_
    0.47
    Act Density 0.002%

    No Known Activations