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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ्षक
    -0.07
    _owned
    -0.07
     Allowed
    -0.06
    ्थन
    -0.06
    ừa
    -0.06
    _uniform
    -0.06
    Transformation
    -0.06
    -uppercase
    -0.06
     Diamond
    -0.06
     enfants
    -0.06
    POSITIVE LOGITS
    _HOOK
    0.07
    ."},↵
    0.06
    pcl
    0.06
     med
    0.06
     🙂
    0.06
    _BLE
    0.06
    Crud
    0.06
    legates
    0.06
     Olymp
    0.06
     decisive
    0.06
    Act Density 0.062%

    No Known Activations