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
    _ui
    -0.07
    both
    -0.06
     Highlands
    -0.06
    カ
    -0.06
     unset
    -0.06
    _quotes
    -0.06
     Fare
    -0.06
     skill
    -0.06
     Slee
    -0.06
    (Box
    -0.06
    POSITIVE LOGITS
    Ars
    0.07
     männ
    0.07
    =Math
    0.06
    خص
    0.06
    ΟΛΟΓ
    0.06
    وف
    0.06
     enchant
    0.06
    UNIT
    0.06
     хотел
    0.06
     recession
    0.06
    Act Density 0.078%

    No Known Activations