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

    Neuronpedia

    INDEX
    Explanations

    empowerment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ibt
    -0.07
     đàn
    -0.06
    Unix
    -0.06
     airlines
    -0.06
    okie
    -0.06
     ANN
    -0.06
    μορ
    -0.06
    amespace
    -0.06
    volent
    -0.06
    _flash
    -0.06
    POSITIVE LOGITS
     INDIRECT
    0.07
     kulak
    0.07
    (pred
    0.06
    ,-
    0.06
     inverted
    0.06
     contradictions
    0.06
    实施
    0.06
     Gang
    0.06
     nigeria
    0.06
     —↵
    0.06
    Act Density 0.051%

    No Known Activations