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

    Neuronpedia

    INDEX
    Explanations

    international agreements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     `%
    -0.08
    (async
    -0.07
     INCIDENTAL
    -0.07
    _dis
    -0.07
    .STATE
    -0.07
    sburg
    -0.06
    -0.06
    .Sh
    -0.06
    .provider
    -0.06
    -comp
    -0.06
    POSITIVE LOGITS
     ál
    0.07
    -static
    0.07
    .sess
    0.07
    妥
    0.07
    暑假
    0.07
    崃
    0.07
    _stuff
    0.07
    稳固
    0.07
    щин
    0.07
    :A
    0.07
    Act Density 0.022%

    No Known Activations