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

    Neuronpedia

    INDEX
    Explanations

    instances of exclamations and special characters indicating emphasis or strong feelings

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

    emphasis markers and placeholders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     numberWith
    -0.69
    yntaxException
    -0.64
     ContentValues
    -0.63
     setId
    -0.60
    Hatch
    -0.59
    chaise
    -0.58
     MotionEvent
    -0.57
    minton
    -0.57
    ention
    -0.56
    stination
    -0.56
    POSITIVE LOGITS
    3
    0.68
     MMM
    0.60
    !!!
    0.59
    xxx
    0.57
    ooo
    0.57
     "../../../
    0.56
    >>>
    0.54
    Ummm
    0.53
     !!!
    0.52
    iii
    0.52
    Act Density 0.047%

    No Known Activations