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

    Neuronpedia

    INDEX
    Explanations

    had followed by speech verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fledged
    1.85
     comfortable
    1.76
     Comfortable
    1.74
     দেরি
    1.67
    unoassay
    1.66
     человеком
    1.65
     pleasures
    1.64
    郸
    1.63
     elective
    1.63
    otur
    1.61
    POSITIVE LOGITS
    라면
    1.94
    ்
    1.84
    quela
    1.67
    народ
    1.53
     کہتے
    1.53
    ्टी
    1.50
    ヨタ
    1.49
    Γ
    1.48
    োয়ার
    1.47
    тся
    1.45
    Act Density 0.003%

    No Known Activations