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

    Neuronpedia

    INDEX
    Explanations

    covered/inside

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -viol
    -0.07
     metab
    -0.06
     TEMPLATE
    -0.06
     unpopular
    -0.06
     Maxwell
    -0.06
    :Boolean
    -0.06
    报刊
    -0.06
    ﯘ
    -0.06
     assembled
    -0.06
     Angela
    -0.06
    POSITIVE LOGITS
     BorderSide
    0.07
     بسبب
    0.07
    orderBy
    0.07
    _PROC
    0.07
     thats
    0.06
    بارك
    0.06
    Solid
    0.06
    同事们
    0.06
    rapy
    0.06
     בקלות
    0.06
    Act Density 0.042%

    No Known Activations