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

    Neuronpedia

    INDEX
    Explanations

    conjunctions leading to outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     whatnot
    1.20
    ्स
    0.97
    rogens
    0.95
    ियों
    0.93
     вовсе
    0.90
     blijft
    0.89
    an
    0.85
     především
    0.85
    s
    0.84
     Jahren
    0.81
    POSITIVE LOGITS
    る
    0.84
    ה
    0.83
    з
    0.83
    て
    0.82
    пи
    0.76
    た
    0.76
    ど
    0.76
    )'
    0.75
    ında
    0.73
    ף
    0.73
    Act Density 0.164%

    No Known Activations