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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dünyanın
    -0.08
     sonic
    -0.08
     bone
    -0.07
     mein
    -0.07
     DISCLAIM
    -0.07
     Wenn
    -0.07
     lemon
    -0.07
    _ASS
    -0.07
     doch
    -0.07
    通り
    -0.07
    POSITIVE LOGITS
    5
    0.08
    3
    0.07
    2
    0.07
    al
    0.07
    AL
    0.06
     AC
    0.06
    L
    0.06
    aul
    0.06
    ag
    0.06
     تاث
    0.06
    Act Density 0.060%

    No Known Activations