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

    Neuronpedia

    INDEX
    Explanations

    references to specific entities and their classifications or grades

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

    Letters followed by a parenthesis or colon

    np_acts-logits-general · gemini-2.0-flash

    A, B, C, D labels or items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Vikipedi
    -0.65
    Rè
    -0.55
    — 
    -0.54
    pairs
    -0.53
    Pairs
    -0.52
    PAIR
    -0.51
    uddles
    -0.51
     Lard
    -0.50
    AddRange
    -0.49
     Cra
    -0.49
    POSITIVE LOGITS
    ValueGenerated
    0.53
    apunov
    0.52
    PageModule
    0.50
    GRANTED
    0.50
    ENOMEM
    0.49
    Importante
    0.48
    VideoCapture
    0.48
    êques
    0.48
    subplots
    0.47
     plotly
    0.47
    Act Density 0.833%

    No Known Activations