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
    %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
    -0.06
    .loggedIn
    -0.06
     FormData
    -0.06
    @Entity
    -0.06
    please
    -0.06
    hist
    -0.06
     учнів
    -0.06
    τικός
    -0.06
    alse
    -0.05
    ख
    -0.05
    POSITIVE LOGITS
     skup
    0.07
     Timeline
    0.07
    bucks
    0.07
    وير
    0.07
    _EDGE
    0.07
     Rows
    0.06
     Ex
    0.06
    apl
    0.06
     Filed
    0.06
    زو
    0.06
    Act Density 0.029%

    No Known Activations