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
    ア
    -0.08
     hawk
    -0.07
    母
    -0.07
     pwd
    -0.07
     punk
    -0.07
     MAC
    -0.07
     Ford
    -0.07
     hy
    -0.07
     término
    -0.07
     ampl
    -0.06
    POSITIVE LOGITS
    相比于
    0.07
    striction
    0.07
    Annotations
    0.07
     //(
    0.07
     Sporting
    0.07
    ög
    0.07
    ActivityCreated
    0.07
    (do
    0.07
    (strpos
    0.07
    ffective
    0.07
    Act Density 0.004%

    No Known Activations