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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation and symbols

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

    LaTeX math expressions and citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    </i>
    -0.42
     in
    -0.42
     the
    -0.41
     including
    -0.41
    </b>
    -0.39
    ChildIndex
    -0.39
     for
    -0.39
     to
    -0.39
     The
    -0.38
     It
    -0.37
    POSITIVE LOGITS
     autorytatywna
    0.70
     kasarigan
    0.69
     surla
    0.65
    +#+#
    0.64
    pecabe
    0.63
     Infórmanos
    0.62
     Utf
    0.59
    Personendaten
    0.58
    Билгалдахарш
    0.55
     &___
    0.54
    Act Density 0.002%

    No Known Activations