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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    feat
    -0.07
    378
    -0.07
     Suppose
    -0.06
    147
    -0.06
     assoc
    -0.06
     ya
    -0.06
     plu
    -0.06
    hů
    -0.06
    ULER
    -0.06
     radial
    -0.06
    POSITIVE LOGITS
    _land
    0.08
    _SESSION
    0.07
    tom
    0.07
     offerings
    0.06
    _Customer
    0.06
    ंपन
    0.06
     حم
    0.06
    頁
    0.06
     انسان
    0.06
     SAME
    0.06
    Act Density 0.043%

    No Known Activations