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
    ropolis
    -0.08
    كني
    -0.07
    ov
    -0.07
    خالف
    -0.07
    分かる
    -0.07
     קופ
    -0.07
    �
    -0.06
    mpi
    -0.06
     Solic
    -0.06
    ecedor
    -0.06
    POSITIVE LOGITS
    $values
    0.08
     môn
    0.07
    常年
    0.07
     relacion
    0.07
     things
    0.07
    /H
    0.07
    🏅
    0.07
     Listed
    0.07
    Will
    0.07
    uctor
    0.07
    Act Density 0.066%

    No Known Activations