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

    Neuronpedia

    INDEX
    Explanations

    tokens with low-precedence or unstructured whitespace formatting

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

    HTML attribute class followed by equals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ก
    -0.28
     habet
    -0.27
    TS
    -0.27
    真
    -0.26
    v
    -0.26
    CheckedChanged
    -0.26
    โ
    -0.25
    c
    -0.24
     tercio
    -0.24
     senderismo
    -0.24
    POSITIVE LOGITS
    ✨:
    1.09
     surla
    0.91
     समीक्षक
    0.90
    <unused14>
    0.89
    <unused41>
    0.89
    <unused23>
    0.88
    <unused28>
    0.88
    <unused16>
    0.88
    [@BOS@]
    0.88
    <unused8>
    0.88
    Act Density 0.027%

    No Known Activations