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

    Neuronpedia

    INDEX
    Explanations

    unstructured data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ґ
    -0.06
     geen
    -0.06
    pk
    -0.06
    _XML
    -0.06
    they
    -0.06
     ettiği
    -0.06
     Cara
    -0.06
    'A
    -0.06
    iang
    -0.06
     jiného
    -0.06
    POSITIVE LOGITS
    艺术
    0.07
     дитини
    0.07
     accident
    0.06
     Foto
    0.06
     visualize
    0.06
     Prosec
    0.06
     heightened
    0.06
    ':['
    0.06
    experiment
    0.06
     bec
    0.06
    Act Density 0.016%

    No Known Activations