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

    Neuronpedia

    INDEX
    Explanations

    review

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .FromSeconds
    -0.07
     boob
    -0.07
     �
    -0.06
    women
    -0.06
     Writers
    -0.06
     svob
    -0.06
    ливі
    -0.06
    Expansion
    -0.06
    .container
    -0.06
     VERSION
    -0.06
    POSITIVE LOGITS
     IMO
    0.07
     оцен
    0.06
    -tooltip
    0.06
     geopolitical
    0.06
    多少
    0.06
    IMO
    0.06
     marvel
    0.06
    영어
    0.06
    _lahir
    0.06
    리그
    0.06
    Act Density 0.009%

    No Known Activations