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

    Neuronpedia

    INDEX
    Explanations

    factors forming or leading to outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     because
    0.84
    because
    0.83
     involvement
    0.83
     associated
    0.80
     involves
    0.76
    associated
    0.75
     Involvement
    0.75
     kvůli
    0.74
     কারন
    0.74
     dahil
    0.73
    POSITIVE LOGITS
     membentuk
    1.39
     formando
    1.17
     Collectively
    1.15
     collectively
    1.13
     totalling
    1.11
     culminated
    1.06
     together
    1.05
     मिलकर
    1.04
     vormen
    1.04
    形成
    1.04
    Act Density 0.221%

    No Known Activations