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

    Neuronpedia

    INDEX
    Explanations

    in luck! range Philip Vern

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    {
    0.90
    ORO
    0.82
    columns
    0.81
    yards
    0.79
    reliability
    0.79
     Gardens
    0.79
    ts
    0.76
    mal
    0.76
    mnist
    0.76
    re
    0.75
    POSITIVE LOGITS
    璨
    0.84
    ੇ
    0.82
    нский
    0.81
     Также
    0.81
    女
    0.78
    ковый
    0.78
     Ró
    0.77
     भी
    0.76
    하는
    0.76
     детский
    0.76
    Act Density 0.000%

    No Known Activations