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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     herum
    0.73
     leaping
    0.70
    start
    0.70
    ᚋ
    0.68
     startGame
    0.68
     start
    0.67
     Start
    0.67
    ებული
    0.67
     Swallow
    0.67
     Day
    0.64
    POSITIVE LOGITS
     உள்ளது
    0.88
     cauza
    0.88
     умови
    0.86
     disposiciones
    0.84
     jumlah
    0.82
    രിക്കും
    0.81
     daños
    0.81
     топлива
    0.81
     Verfügung
    0.81
     presentan
    0.81
    Act Density 0.003%

    No Known Activations