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

    Neuronpedia

    INDEX
    Explanations

    ocene

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ulate
    -0.07
     compete
    -0.07
    (drop
    -0.06
    据
    -0.06
    ank
    -0.06
    OGRAPH
    -0.06
    ulation
    -0.06
    ор
    -0.06
     출장
    -0.06
     답변
    -0.06
    POSITIVE LOGITS
    ;base
    0.07
    .MaximizeBox
    0.06
    TF
    0.06
    /REC
    0.06
    .subplot
    0.06
    *t
    0.06
    .Tensor
    0.06
    _ssh
    0.06
    .UTF
    0.06
     UW
    0.06
    Act Density 0.032%

    No Known Activations