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

    Neuronpedia

    INDEX
    Explanations

    points and references in a structured format, particularly in data or citations

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

    Followed by "b" or "B"

    np_acts-logits-general · gemini-2.0-flash

    parenthesis followed by b or B

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uws
    -0.53
    A
    -0.51
     GetEnumerator
    -0.49
    ometra
    -0.45
    ❋
    -0.43
    fu
    -0.43
    fus
    -0.42
     A
    -0.41
     Knie
    -0.41
    verre
    -0.40
    POSITIVE LOGITS
     b
    2.02
     B
    1.74
    b
    1.70
    B
    1.44
     getB
    1.29
    getB
    1.27
     ب
    1.13
     б
    1.12
    ｂ
    0.98
    ب
    0.82
    Act Density 0.402%

    No Known Activations