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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and if

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .”
    0.45
     हेतु
    0.38
     técnicos
    0.38
    有个
    0.38
     Consultado
    0.37
    Typically
    0.37
    有個
    0.37
     extraordinaire
    0.37
    ؛
    0.37
     nahezu
    0.37
    POSITIVE LOGITS
     અને
    0.59
     आणि
    0.57
     और
    0.55
    和
    0.54
     ਅਤੇ
    0.52
    ിക്കുകയും
    0.52
     없고
    0.52
     және
    0.49
    如果
    0.49
    และการ
    0.49
    Act Density 0.041%

    No Known Activations