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
    repr
    -0.06
    thest
    -0.06
    ellaneous
    -0.06
     and
    -0.06
    Com
    -0.06
    ていない
    -0.06
     Supern
    -0.06
    selling
    -0.06
    nung
    -0.06
    _stand
    -0.06
    POSITIVE LOGITS
    5
    0.08
    ６
    0.08
    1
    0.07
    0
    0.07
    了一
    0.07
    20
    0.07
    2
    0.07
    3
    0.07
    6
    0.07
    ա
    0.07
    Act Density 0.132%

    No Known Activations