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

    Neuronpedia

    INDEX
    Explanations

    sequences of repeated characters or symbols

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

    ---------- -------- --------

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    the
    -0.37
     paille
    -0.33
    y
    -0.33
    typeName
    -0.32
     Năm
    -0.31
    tv
    -0.31
    tw
    -0.31
    W
    -0.30
    tow
    -0.30
    al
    -0.30
    POSITIVE LOGITS
     bisa
    1.73
     Bisa
    1.54
    Bisa
    1.48
    bisa
    1.36
    Could
    0.90
    CanBe
    0.86
     Could
    0.86
     could
    0.85
    sizeCache
    0.83
    could
    0.82
    Act Density 0.003%

    No Known Activations