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

    Neuronpedia

    INDEX
    Explanations

    programming code keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    jük
    0.81
    snp
    0.81
    ▟
    0.81
     மதி
    0.80
     imassa
    0.79
    والفقار
    0.78
     dhammo
    0.76
    βολ
    0.76
    iacute
    0.76
    说了
    0.75
    POSITIVE LOGITS
    =
    0.78
     rež
    0.77
    ailand
    0.67
     Expenses
    0.66
     Unix
    0.66
     型
    0.66
    સી
    0.64
     fors
    0.63
    agens
    0.63
    ="
    0.63
    Act Density 0.001%

    No Known Activations