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

    Neuronpedia

    INDEX
    Explanations

    if the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    \}
    0.76
     equid
    0.76
     vů
    0.76
    atribut
    0.76
    rrbracket
    0.73
     STOP
    0.73
     veniam
    0.73
     Тимо
    0.72
     aver
    0.71
     Kontext
    0.71
    POSITIVE LOGITS
    残念
    0.96
    ñada
    0.96
    គ
    0.88
    తర
    0.81
     विविध
    0.80
    ੁ
    0.80
    ≖
    0.79
    Scenes
    0.79
    isPlaying
    0.78
    ঠা
    0.78
    Act Density 0.002%

    No Known Activations