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

    Neuronpedia

    INDEX
    Explanations

    100

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Substitute
    -0.07
     Dane
    -0.06
    .templates
    -0.06
    Defense
    -0.06
     SUBSTITUTE
    -0.06
     purification
    -0.06
     Ballet
    -0.06
    _SERVER
    -0.06
    Root
    -0.06
     spokesperson
    -0.06
    POSITIVE LOGITS
    :max
    0.07
     willing
    0.07
     최저
    0.06
     fclose
    0.06
    isEmpty
    0.06
     ties
    0.06
     До
    0.06
    MAS
    0.06
    ันธ
    0.06
     Prob
    0.06
    Act Density 0.011%

    No Known Activations