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

    Neuronpedia

    INDEX
    Explanations

    throw

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Samuel
    -0.08
     Vegas
    -0.08
    "--
    -0.08
    法庭
    -0.07
     ServiceProvider
    -0.07
    )/
    -0.07
    yses
    -0.07
     "{
    -0.07
    _Open
    -0.07
     avenues
    -0.07
    POSITIVE LOGITS
    散热
    0.08
     lanç
    0.07
    genic
    0.07
     Enhanced
    0.07
    Ủ
    0.07
    ált
    0.07
    _ordered
    0.07
     halten
    0.07
    _raw
    0.07
    аци
    0.07
    Act Density 0.009%

    No Known Activations