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

    Neuronpedia

    INDEX
    Explanations

    special formatting elements and symbols commonly used in code or mathematical contexts

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

    code formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    awtextra
    -0.53
     bParam
    -0.52
    enumi
    -0.52
    SuppressMessage
    -0.47
     Савезне
    -0.45
    >=</
    -0.45
    ieteur
    -0.44
    _|
    -0.42
     incomplète
    -0.42
    Dade
    -0.42
    POSITIVE LOGITS
    Manbalar
    0.63
    ágenes
    0.62
    ⤒
    0.50
    ientôt
    0.45
    posedge
    0.44
     camicia
    0.44
     ainfi
    0.44
    före
    0.44
     Walkover
    0.44
     mikina
    0.43
    Act Density 0.035%

    No Known Activations