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

    Neuronpedia

    INDEX
    Explanations

    groupId

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     آثار
    -0.07
    奶
    -0.07
    ैर
    -0.07
     INCLUDED
    -0.07
    (py
    -0.06
    _inverse
    -0.06
     bizi
    -0.06
    -lfs
    -0.06
     bounced
    -0.06
     Larry
    -0.06
    POSITIVE LOGITS
    Clinton
    0.07
     Context
    0.07
     Compet
    0.07
    lášení
    0.06
    structor
    0.06
    这种
    0.06
    mando
    0.06
    λογία
    0.06
     gli
    0.06
    .Col
    0.06
    Act Density 0.000%

    No Known Activations