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

    Neuronpedia

    INDEX
    Explanations

    phone numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    äude
    0.54
    餑
    0.46
    硙
    0.46
    𒈠
    0.45
    糁
    0.43
    枌
    0.42
     provoked
    0.42
    үүл
    0.41
     senyawa
    0.41
    稦
    0.41
    POSITIVE LOGITS
    9
    0.53
     phone
    0.52
    -(
    0.52
     telefono
    0.50
    8
    0.47
     телефон
    0.47
    2
    0.46
    0.46
    XXXXXXXX
    0.45
     teléfono
    0.45
    Act Density 0.004%

    No Known Activations