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
     democracy
    -0.08
     kWh
    -0.07
    (percent
    -0.07
     society
    -0.07
     ос
    -0.07
    usa
    -0.06
    몬
    -0.06
     listeners
    -0.06
    -rays
    -0.06
    CAP
    -0.06
    POSITIVE LOGITS
    .TestCheck
    0.07
    اپ
    0.06
     Claud
    0.06
     bü
    0.06
     frankfurt
    0.06
     �
    0.06
    .getHours
    0.06
    _test
    0.06
     }\
    0.06
    _PHP
    0.06
    Act Density 0.041%

    No Known Activations