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

    Neuronpedia

    INDEX
    Explanations

    politics and history

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ional
    -0.07
     Sandbox
    -0.07
     MED
    -0.07
    idth
    -0.06
    erno
    -0.06
     PEN
    -0.06
    YN
    -0.06
    np
    -0.06
     Bolton
    -0.06
     شم
    -0.06
    POSITIVE LOGITS
    .optimizer
    0.07
    义
    0.06
    .Information
    0.06
     Args
    0.06
    _named
    0.06
    .assertRaises
    0.06
    templates
    0.06
     disagreement
    0.06
    [out
    0.06
    .isAdmin
    0.06
    Act Density 0.072%

    No Known Activations