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

    Neuronpedia

    INDEX
    Explanations

    took

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _TRAN
    -0.07
    PAL
    -0.06
    ween
    -0.06
     Cleans
    -0.06
     Cure
    -0.06
    activated
    -0.06
    Ấ
    -0.06
    Autor
    -0.06
    OutputStream
    -0.06
    铺
    -0.06
    POSITIVE LOGITS
    .getBoolean
    0.08
    [B
    0.07
     bereits
    0.07
     nemůže
    0.07
     mulher
    0.07
     zijn
    0.06
    _delta
    0.06
     homme
    0.06
    (toolbar
    0.06
    /company
    0.06
    Act Density 0.013%

    No Known Activations