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

    Neuronpedia

    INDEX
    Explanations

    action census dominate jab role

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    د
    0.50
    䔉
    0.46
     koh
    0.43
    ج
    0.43
    كار
    0.42
     éditions
    0.41
    ኣ
    0.41
    大型
    0.40
    ುದ
    0.40
    SCAPE
    0.40
    POSITIVE LOGITS
     действия
    0.56
     следующие
    0.52
     пять
    0.52
    łość
    0.52
    "]
    0.50
    łości
    0.50
     начала
    0.50
     далее
    0.48
     состояния
    0.48
     onslaught
    0.48
    Act Density 0.000%

    No Known Activations