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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     some
    0.47
     frecu
    0.46
     hindered
    0.45
     passively
    0.43
     horsepower
    0.43
     negated
    0.42
     índices
    0.42
     negation
    0.42
     neutrinos
    0.42
     ribonucle
    0.42
    POSITIVE LOGITS
    薰
    0.34
    咨询
    0.33
    ileen
    0.33
    File
    0.33
    Anna
    0.32
    6
    0.32
    8
    0.31
    ６
    0.31
    StartTime
    0.31
     상담
    0.30
    Act Density 0.102%

    No Known Activations