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

    Neuronpedia

    INDEX
    Explanations

    place names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    phyl
    -0.07
    COPE
    -0.07
    _absolute
    -0.07
     is
    -0.07
    rz
    -0.07
    ку
    -0.07
    ується
    -0.06
    بح
    -0.06
    ")]
    -0.06
     steals
    -0.06
    POSITIVE LOGITS
    (:,
    0.06
    \Json
    0.06
    .FloatTensor
    0.06
    OSP
    0.06
     Forward
    0.06
    _Control
    0.06
     TCP
    0.06
     Tiny
    0.06
    VectorXd
    0.05
    уг
    0.05
    Act Density 0.246%

    No Known Activations