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

    Neuronpedia

    INDEX
    Explanations

    wax, sugar, algorithm, Vito

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    umble
    0.50
    ಿಯೂ
    0.49
     उपलब्धता
    0.48
     мою
    0.48
     시
    0.48
     встреча
    0.47
     моём
    0.47
    iot
    0.47
     monasteries
    0.46
     Siam
    0.46
    POSITIVE LOGITS
    downs
    0.55
    Hallo
    0.55
    Preis
    0.53
    Seit
    0.53
    Repost
    0.52
    Sehr
    0.52
    Distance
    0.52
    Does
    0.51
    مر
    0.50
    To
    0.50
    Act Density 0.001%

    No Known Activations