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

    Neuronpedia

    INDEX
    Explanations

    if

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Acts
    -0.08
    Acts
    -0.07
     sabe
    -0.07
     @"";↵
    -0.07
     cites
    -0.06
    _tcp
    -0.06
    _an
    -0.06
    }↵↵↵↵↵
    -0.06
    ()">↵
    -0.06
     {};
    -0.06
    POSITIVE LOGITS
    .changed
    0.07
    .shopping
    0.06
     valuation
    0.06
    uitar
    0.06
    olygon
    0.06
    ADDING
    0.06
     отдель
    0.06
     tournaments
    0.06
     얼굴
    0.06
     improving
    0.06
    Act Density 0.003%

    No Known Activations