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

    Neuronpedia

    INDEX
    Explanations

    three followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ජ
    0.43
    િમ
    0.42
    ामु
    0.41
    علم
    0.41
    iophene
    0.41
    ु
    0.41
    ABASE
    0.39
    ORK
    0.38
     afsl
    0.38
     dissatisf
    0.38
    POSITIVE LOGITS
     month
    0.53
     minuto
    0.52
    minute
    0.49
     hundred
    0.48
    minutes
    0.47
     minutes
    0.46
     dollars
    0.46
    month
    0.45
    months
    0.45
     Months
    0.45
    Act Density 0.000%

    No Known Activations