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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Visibility
    -0.08
    ��
    -0.07
    𬤊
    -0.07
    楒
    -0.07
    cosity
    -0.07
    ész
    -0.07
    ui
    -0.07
    鄄
    -0.07
    ｮ
    -0.07
    雱
    -0.07
    POSITIVE LOGITS
     słab
    0.07
     Coinbase
    0.07
     Trap
    0.07
     Broker
    0.07
    .bo
    0.06
    骱
    0.06
    Slides
    0.06
    brain
    0.06
     dbname
    0.06
    Pad
    0.06
    Act Density 0.003%

    No Known Activations