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

    Neuronpedia

    INDEX
    Explanations

    symbols and formatting indicators used in coding or structured data contexts

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

    mathematical expressions and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     zijne
    -0.39
    Lähteet
    -0.38
     plaît
    -0.37
     Taktlose
    -0.36
     mijne
    -0.36
     Vgl
    -0.35
    Зноскі
    -0.34
     Vernunft
    -0.34
    lesias
    -0.34
     Saltar
    -0.33
    POSITIVE LOGITS
    ➟
    0.61
    setVerticalGroup
    0.54
    évaluateur
    0.53
    posedge
    0.53
     ***!
    0.52
    putin
    0.52
    awtextra
    0.51
     pinulongan
    0.51
    IsContent
    0.50
     متعلقه
    0.50
    Act Density 0.005%

    No Known Activations