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

    Neuronpedia

    INDEX
    Explanations

    at a time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    די
    0.68
    හ
    0.60
    خراج
    0.59
     hid
    0.59
     _.
    0.56
     Trock
    0.56
     transcript
    0.56
    transcript
    0.56
     trans
    0.55
     há
    0.55
    POSITIVE LOGITS
    iforme
    0.70
    ഘോഷ
    0.66
    Pom
    0.65
     Kat
    0.64
     Pom
    0.64
     Cint
    0.63
    TEGER
    0.62
    INO
    0.62
    ినీ
    0.61
    ja
    0.61
    Act Density 0.122%

    No Known Activations