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

    Neuronpedia

    INDEX
    Explanations

    specific word following common words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     enamel
    0.42
     বলিব
    0.41
     "("
    0.39
    ("("
    0.39
    ತಕ್ಕ
    0.39
     facteur
    0.38
     rufo
    0.38
    屬
    0.38
     Crypt
    0.38
     লেখ
    0.37
    POSITIVE LOGITS
    haran
    0.40
    Ws
    0.39
    ukkan
    0.39
    Fear
    0.39
    󠁮
    0.39
    doo
    0.39
     gyors
    0.38
    ort
    0.37
     Fear
    0.37
    ard
    0.37
    Act Density 0.000%

    No Known Activations