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

    Neuronpedia

    INDEX
    Explanations

    codes like 'N', 'Q', 'G', 'D', 'E'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     也
    0.41
     చిత్ర
    0.38
     सूफ़ी
    0.38
     burials
    0.38
     এমন
    0.36
     ሳይ
    0.36
    爵
    0.36
     ప్రభావ
    0.35
     ఇప్పుడు
    0.35
    𒄑
    0.35
    POSITIVE LOGITS
     Ari
    0.38
    F
    0.37
    함을
    0.37
     =
    0.36
     P
    0.36
     Extract
    0.36
     Seq
    0.36
     Número
    0.35
    P
    0.35
     acronym
    0.35
    Act Density 0.035%

    No Known Activations