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

    Neuronpedia

    INDEX
    Explanations

    numerical data or identifiers

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

    Non-English words, code, and symbols

    np_acts-logits-general · gemini-2.0-flash

    special characters and multilingual words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tartalomajánló
    -0.85
    __*/
    -0.83
     CanadaChoose
    -0.78
     kasarigan
    -0.70
    ArrowToggle
    -0.68
     <<<<<<<<<<<<<<
    -0.65
    NewReader
    -0.65
     дописавши
    -0.65
     cref
    -0.63
    ellemző
    -0.62
    POSITIVE LOGITS
    Geplaatst
    0.47
    äinen
    0.46
    ButterKnife
    0.46
    ksesta
    0.44
     زدن
    0.43
     يتيمه
    0.43
    expandindo
    0.43
    पन
    0.42
     vaz
    0.42
    larıyla
    0.41
    Act Density 0.007%

    No Known Activations