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

    Neuronpedia

    INDEX
    Explanations

    counting number of items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     或
    0.90
    或
    0.88
    rightsquigarrow
    0.88
     أو
    0.87
    <unused2162>
    0.86
     или
    0.86
     または
    0.85
    ्यारह
    0.85
     несколь
    0.85
     atau
    0.84
    POSITIVE LOGITS
     times
    0.88
    times
    0.84
    decimal
    0.78
     Times
    0.74
    грама
    0.73
    грамма
    0.72
    Times
    0.71
    辆
    0.71
    ప్తి
    0.68
    вка
    0.65
    Act Density 0.157%

    No Known Activations