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

    Neuronpedia

    INDEX
    Explanations

    phone number regex

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Т
    0.91
    ஆ
    0.89
    они
    0.88
    iu
    0.87
    Н
    0.86
    아
    0.86
    À
    0.86
    ан
    0.85
    S
    0.84
    ger
    0.83
    POSITIVE LOGITS
     calculus
    0.85
     cannons
    0.81
     barcodes
    0.80
     marines
    0.80
     bilinear
    0.79
     Barre
    0.78
     Acme
    0.78
     calculators
    0.77
     Buffer
    0.76
     hinges
    0.76
    Act Density 0.000%

    No Known Activations