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

    Neuronpedia

    INDEX
    Explanations

    symbols and punctuation marks

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

    →

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    StructEnd
    -0.47
    DockStyle
    -0.42
     surla
    -0.41
    ThroughAttribute
    -0.41
    rungsseite
    -0.41
     Audiodateien
    -0.40
    :✨
    -0.39
    KURZBESCHREIBUNG
    -0.38
     تضيفلها
    -0.38
    хьтан
    -0.38
    POSITIVE LOGITS
    fromnode
    0.43
    جغرافيا
    0.41
    hamdu
    0.40
    StatusBadRequest
    0.40
    ürnberg
    0.40
    wning
    0.39
    hotra
    0.39
    中略
    0.38
    auen
    0.38
     CTC
    0.38
    Act Density 0.030%

    No Known Activations