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

    Neuronpedia

    INDEX
    Explanations

    varies text sources snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Risk
    -0.07
    roof
    -0.07
    risk
    -0.07
    推
    -0.07
    tiler
    -0.06
     年
    -0.06
     strtotime
    -0.06
    dates
    -0.06
    處
    -0.06
    idges
    -0.06
    POSITIVE LOGITS
    átor
    0.07
     indoors
    0.07
     USDA
    0.06
    атор
    0.06
    icut
    0.06
     monthly
    0.06
     equip
    0.06
     proposes
    0.06
    اع
    0.06
     less
    0.06
    Act Density 0.000%

    No Known Activations