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

    Neuronpedia

    INDEX
    Explanations

    determined

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .CLASS
    -0.07
    gorm
    -0.07
    _sites
    -0.06
    Meta
    -0.06
    (conv
    -0.06
    标题
    -0.06
    Timer
    -0.06
    もしれない
    -0.06
    (Card
    -0.06
    Chess
    -0.06
    POSITIVE LOGITS
    .ask
    0.06
     initialValues
    0.06
    unya
    0.06
    .faces
    0.06
    ंब
    0.06
    ̣c
    0.06
     rulings
    0.06
     На
    0.06
     settlers
    0.06
    '));
↵
    0.06
    Act Density 0.003%

    No Known Activations