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

    Neuronpedia

    INDEX
    Explanations

    software, tools, and guides

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     that
    1.67
    ור
    1.61
    >
    1.41
    ות
    1.35
    {
    1.35
    ,"
    1.33
    ,”
    1.32
    Y
    1.30
    That
    1.29
    ;
    1.29
    POSITIVE LOGITS
    س
    1.63
    с
    1.46
    d
    1.14
    ंबकीय
    1.07
    j
    1.07
     añade
    1.06
    سلم
    1.06
    DeferredGroup
    1.06
     enzimas
    1.05
    t
    1.05
    Act Density 0.004%

    No Known Activations