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

    Neuronpedia

    INDEX
    Explanations

    characters or words in various non-Latin scripts and languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    non-english characters and multilingual phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    as
    -0.37
     or
    -0.36
    f
    -0.35
    is
    -0.34
    rig
    -0.32
    nahme
    -0.32
    ing
    -0.32
    I
    -0.32
    c
    -0.32
     Pro
    -0.31
    POSITIVE LOGITS
     betweenstory
    0.95
     nahilalakip
    0.76
     Geſch
    0.71
     Verſ
    0.71
    majánló
    0.71
     StatefulWidget
    0.70
     nakalista
    0.69
     queſta
    0.68
     كومونز
    0.67
    transQ
    0.66
    Act Density 0.043%

    No Known Activations