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

    Neuronpedia

    INDEX
    Explanations

    phone international

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    erves
    0.46
    ayn
    0.45
    IANA
    0.44
    ्या
    0.43
    iver
    0.43
    ेंट्स
    0.42
    othes
    0.42
    iffer
    0.42
    opp
    0.42
    alam
    0.42
    POSITIVE LOGITS
     probe
    0.48
     bogus
    0.47
    стер
    0.46
    හෝ
    0.46
     spurious
    0.45
     telepon
    0.45
     téléphone
    0.45
     pozn
    0.44
     risultato
    0.44
     telef
    0.44
    Act Density 0.003%

    No Known Activations