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

    Neuronpedia

    INDEX
    Explanations

    sequences of commas or whitespace in a structured format

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

    html div and code contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DebuggerNonUser
    -0.47
    BeginContext
    -0.44
    oplayer
    -0.43
     ویکی‌پدیا
    -0.42
    DockStyle
    -0.42
    awtextra
    -0.42
     Ranger
    -0.40
    setVerticalGroup
    -0.40
    GraphicsUnit
    -0.40
     raso
    -0.39
    POSITIVE LOGITS
     Italijani
    0.55
    WithIOException
    0.54
     Administrativna
    0.51
     pioggia
    0.45
    seits
    0.45
    ConstraintMaker
    0.45
     duele
    0.45
    Distribución
    0.44
     toekomst
    0.44
     gatto
    0.43
    Act Density 0.260%

    No Known Activations