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

    Neuronpedia

    INDEX
    Explanations

    discretionary trips; yogurt,

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sínt
    0.41
     shrinks
    0.41
    >',
    0.40
    Sí
    0.39
    और
    0.39
    ච්
    0.39
     hazır
    0.39
    Hval
    0.39
    ແລະ
    0.39
    रो
    0.39
    POSITIVE LOGITS
    breaker
    0.39
    idaire
    0.37
    পত
    0.37
     Stocks
    0.37
     Native
    0.36
     containment
    0.36
     Natives
    0.36
     breaker
    0.35
     backcountry
    0.35
     consortium
    0.34
    Act Density 0.000%

    No Known Activations