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

    Neuronpedia

    INDEX
    Explanations

    technical or mathematical context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     மர
    0.38
     przyczyn
    0.38
    iss
    0.37
    icks
    0.36
     divisors
    0.36
     strengths
    0.36
    夥
    0.36
     pann
    0.35
    xz
    0.35
    HEADER
    0.34
    POSITIVE LOGITS
    गढ़
    0.46
    ামিটার
    0.42
     Mercantile
    0.42
     maestro
    0.42
     unt
    0.41
     maestros
    0.41
     Unt
    0.40
     NTP
    0.40
    ल्क
    0.40
     blink
    0.40
    Act Density 0.008%

    No Known Activations