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

    Neuronpedia

    INDEX
    Explanations

    technical data

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     opp
    0.58
     Measure
    0.58
     temer
    0.57
     دستی
    0.56
     Occurrence
    0.56
    ettle
    0.55
     पर्य
    0.55
     Daniel
    0.55
    왓
    0.55
     Luck
    0.55
    POSITIVE LOGITS
    PAS
    0.90
     paziente
    0.85
    isel
    0.82
     pazienti
    0.81
     joyas
    0.80
     malades
    0.80
     ادارے
    0.77
     possa
    0.77
     varía
    0.76
    থন
    0.75
    Act Density 0.001%

    No Known Activations