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

    Neuronpedia

    INDEX
    Explanations

    numbers and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Or
    -0.91
     Or
    -0.90
    Literal
    -0.87
    원
    -0.82
    ONE
    -0.80
    getOr
    -0.77
    By
    -0.74
     By
    -0.73
    ById
    -0.72
    BY
    -0.72
    POSITIVE LOGITS
     nineteen
    0.87
    十
    0.86
    十六
    0.85
     Sixteen
    0.82
     Nineteen
    0.80
     十
    0.78
     Nineteenth
    0.73
     Джа
    0.68
     Incidents
    0.68
    十七
    0.67
    Act Density 0.345%

    No Known Activations