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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and underscores in the text

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

    specific code constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     juſ
    -0.73
    AndEndTag
    -0.72
    ſchaft
    -0.65
     reaſon
    -0.62
     Inſ
    -0.61
    ſehen
    -0.56
     MainAxisSize
    -0.56
    iſchen
    -0.56
    iſen
    -0.56
     ſol
    -0.55
    POSITIVE LOGITS
    $_.
    0.46
    :].
    0.40
    ].[
    0.40
    ifndef
    0.39
    ::$
    0.39
    CGContext
    0.38
    ="
    0.37
     "
    0.37
    ']->
    0.36
    ⏟
    0.36
    Act Density 0.011%

    No Known Activations