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

    Neuronpedia

    INDEX
    Explanations

    references to studies or reports in academic writing

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

    citations after "by"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     насељу
    -0.39
    seamnă
    -0.38
     męska
    -0.37
     quidem
    -0.36
     quæ
    -0.36
     BytesLike
    -0.35
     mogę
    -0.35
    reamble
    -0.35
     duidelijk
    -0.34
     eenvoudig
    -0.34
    POSITIVE LOGITS
    enumii
    0.60
    enumi
    0.56
    ViewImports
    0.53
     scholars
    0.50
     researchers
    0.50
    談社
    0.48
    +#+
    0.48
     experts
    0.48
     fortn
    0.47
     physicists
    0.47
    Act Density 0.089%

    No Known Activations