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

    Neuronpedia

    INDEX
    Explanations

    usable

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Um
    -0.06
     百度
    -0.06
    :new
    -0.06
    aits
    -0.06
     CEOs
    -0.06
    物
    -0.06
    ]));
    -0.06
    ，
    -0.06
     poner
    -0.06
    vec
    -0.06
    POSITIVE LOGITS
     действия
    0.07
    Father
    0.07
    .StartsWith
    0.06
    (high
    0.06
    لیه
    0.06
     wavelengths
    0.06
    (InitializedTypeInfo
    0.06
    (Double
    0.06
     {}.
    0.06
    рование
    0.06
    Act Density 0.000%

    No Known Activations