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

    Neuronpedia

    INDEX
    Explanations

    for general

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     only
    0.85
     Only
    0.84
     despite
    0.83
    Only
    0.82
    Whilst
    0.79
     solamente
    0.79
     refus
    0.77
     seuls
    0.77
     тільки
    0.76
     só
    0.76
    POSITIVE LOGITS
     गहरा
    0.73
     종합
    0.66
    లై
    0.66
    global
    0.64
    лев
    0.64
    いに
    0.64
     world
    0.64
    総合
    0.63
    栃
    0.62
    worlds
    0.62
    Act Density 0.018%

    No Known Activations