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

    Neuronpedia

    INDEX
    Explanations

    Cook

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _average
    -0.09
    打着
    -0.08
     �
    -0.08
    _theta
    -0.07
     ath
    -0.07
     alguna
    -0.07
     Leon
    -0.07
    _Search
    -0.07
    _embedding
    -0.07
    .ACCESS
    -0.07
    POSITIVE LOGITS
    pies
    0.07
     revamped
    0.07
     Imag
    0.06
     wy
    0.06
     biscuits
    0.06
    pees
    0.06
    emie
    0.06
    moire
    0.06
    エネ
    0.06
     wię
    0.06
    Act Density 0.007%

    No Known Activations