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

    Neuronpedia

    INDEX
    Explanations

    URLs, domain names, technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pir
    0.76
    pir
    0.73
    து
    0.64
    ادو
    0.64
    istir
    0.63
     bounce
    0.61
     Poul
    0.61
     highly
    0.60
     Pir
    0.60
     flock
    0.60
    POSITIVE LOGITS
    मर
    0.80
    옮
    0.75
     conden
    0.74
    rantes
    0.73
    qy
    0.72
    Hayes
    0.71
     যাবেন
    0.71
    czeń
    0.70
    میٹ
    0.70
     functors
    0.69
    Act Density 0.134%

    No Known Activations