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

    Neuronpedia

    INDEX
    Explanations

    number estimations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    系
    -0.07
    ܫ
    -0.07
     lit
    -0.06
     و
    -0.06
    🐸
    -0.06
     Hubb
    -0.06
    谋
    -0.06
    istani
    -0.06
    �
    -0.06
    (section
    -0.06
    POSITIVE LOGITS
    浓度
    0.08
     logarith
    0.07
    iations
    0.07
    _tele
    0.07
     disappearance
    0.07
    İN
    0.07
    'https
    0.07
    好感
    0.07
     collagen
    0.07
     clinically
    0.07
    Act Density 0.033%

    No Known Activations