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

    Neuronpedia

    INDEX
    Explanations

    questions about the extent or degree of certain concepts or conditions

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

    how much or how far

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DoubleQuotes
    -0.63
     beſte
    -0.63
     ſeinen
    -0.60
    ſehen
    -0.59
    migrationBuilder
    -0.59
     dezelve
    -0.58
    LookAnd
    -0.57
    ſchaft
    -0.57
     виправивши
    -0.56
     zoude
    -0.56
    POSITIVE LOGITS
    有多少
    0.57
     насколько
    0.53
     how
    0.52
     कित
    0.42
     Far
    0.40
    どれだけ
    0.39
     extent
    0.39
     tar
    0.39
     far
    0.39
     چقدر
    0.38
    Act Density 0.046%

    No Known Activations