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

    Neuronpedia

    INDEX
    Explanations

    expressions and words indicating surprise or excitement

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

    Strings of repeated letters

    np_acts-logits-general · gemini-2.0-flash

    elongated vowel sounds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    prüche
    -0.58
     snippetHide
    -0.56
    VIAF
    -0.56
     oprot
    -0.56
    tagext
    -0.53
    Bronnen
    -0.52
     nor
    -0.48
    $\{
    -0.48
    ITHER
    -0.47
    laquo
    -0.46
    POSITIVE LOGITS
    aarrggbb
    0.85
    ValueStyle
    0.77
    fromnode
    0.69
    IVEREF
    0.66
    AAA
    0.63
     kasarigan
    0.62
     tetrachloride
    0.61
     Argyle
    0.60
    Aaa
    0.58
     rheumatism
    0.58
    Act Density 0.068%

    No Known Activations