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

    Neuronpedia

    INDEX
    Explanations

    code structure `cols` or `br`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ר
    0.82
    ка
    0.81
    ು
    0.79
    רק
    0.78
     lèvres
    0.75
    u
    0.74
    ب
    0.74
    х
    0.73
    ي
    0.71
    ex
    0.71
    POSITIVE LOGITS
     Thiel
    0.81
     Grover
    0.76
     VRS
    0.73
     Vermeer
    0.73
     Git
    0.73
     Lunch
    0.70
     потребуется
    0.70
     may
    0.70
     verá
    0.70
     will
    0.69
    Act Density 0.003%

    No Known Activations