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

    Neuronpedia

    INDEX
    Explanations

    occurrences of curly braces or similar structural elements in data formats

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

    schema properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ScopeManager
    -0.58
    iffance
    -0.57
    guiente
    -0.54
    InjectAttribute
    -0.53
    msgTypes
    -0.53
     monasterio
    -0.53
    VERTISEMENT
    -0.52
    écnicas
    -0.52
    DockStyle
    -0.52
     ſeinem
    -0.52
    POSITIVE LOGITS
     what
    0.38
     تضيفلها
    0.35
     ujednoznacz
    0.34
     Riv
    0.32
    nologue
    0.32
     hems
    0.31
    stufen
    0.31
     Thing
    0.31
     farms
    0.31
     ground
    0.31
    Act Density 0.002%

    No Known Activations