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

    Neuronpedia

    INDEX
    Explanations

    references to specific measures or classifications related to data

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

    preposition on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Vordergrund
    -0.44
    coroutines
    -0.43
     terdekat
    -0.41
     continúas
    -0.39
    tanleria
    -0.38
    Atsauces
    -0.36
     burbujas
    -0.35
    ViewInit
    -0.35
     cortinas
    -0.35
     Ansprechpartner
    -0.35
    POSITIVE LOGITS
     روی
    0.69
     ועל
    0.67
    onSearch
    0.67
     وعلى
    0.66
    onAdd
    0.65
     platforms
    0.62
     behalf
    0.61
     on
    0.60
    onCancel
    0.58
     On
    0.57
    Act Density 0.268%

    No Known Activations