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

    Neuronpedia

    INDEX
    Explanations

    warnings and disclaimers related to explicit content

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

    warnings or spoilers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    الحياه
    -0.47
     Perubahan
    -0.46
     nemlig
    -0.41
     Kerja
    -0.40
     unidad
    -0.40
    KommentareTeilen
    -0.39
    実現
    -0.39
     nämlich
    -0.38
     flatter
    -0.37
     réalis
    -0.37
    POSITIVE LOGITS
    setVerticalGroup
    0.69
    hoeddwyd
    0.54
    ftagPool
    0.53
     cherchés
    0.52
    WebControls
    0.52
    twimg
    0.50
     pinulongan
    0.48
    LookAnd
    0.45
    findpost
    0.44
    awtextra
    0.44
    Act Density 0.012%

    No Known Activations