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

    Neuronpedia

    INDEX
    Explanations

    prime numbers and national helplines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ारण
    0.59
    弧
    0.55
     round
    0.55
     lifetime
    0.54
    কালীন
    0.52
    স্বরূপ
    0.51
     langer
    0.51
     français
    0.50
    に対し
    0.50
    گیز
    0.49
    POSITIVE LOGITS
     numeri
    0.69
     numbers
    0.68
     Numbers
    0.67
    Tokenizer
    0.66
    गर
    0.65
    န်
    0.65
    val
    0.64
    īj
    0.63
     कुर्
    0.62
    0.62
    Act Density 0.123%

    No Known Activations