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

    Neuronpedia

    INDEX
    Explanations

    organizations and scientific studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     modelo
    -0.08
     Zak
    -0.07
     context
    -0.07
     paz
    -0.06
     Prefix
    -0.06
    /do
    -0.06
     Collect
    -0.06
    -secondary
    -0.06
    .Link
    -0.06
     Blogger
    -0.06
    POSITIVE LOGITS
    (Base
    0.08
    __()↵↵
    0.07
     testCase
    0.07
    Jane
    0.07
    WAIT
    0.07
    }'",
    0.06
    {}",
    0.06
     DEALINGS
    0.06
    なら
    0.06
    距
    0.06
    Act Density 0.004%

    No Known Activations