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

    Neuronpedia

    INDEX
    Explanations

    negations and contractions related to inability or non-existence

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

    Contractions with "n't" or "'"

    np_acts-logits-general · gemini-2.0-flash

    negative contractions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.82
    Personendaten
    -0.75
     الرياضيه
    -0.73
     BoxDecoration
    -0.69
    AnimationsModule
    -0.69
     pinulongan
    -0.67
     '\\;'
    -0.67
    wikidata
    -0.65
    Koordinaten
    -0.64
     requestCode
    -0.63
    POSITIVE LOGITS
    GeneratedCode
    0.50
    Wald
    0.47
    /-/
    0.46
    lapsingToolbar
    0.46
    なお
    0.45
    NOST
    0.44
    .”
    0.42
    主任
    0.42
     proposed
    0.42
    {$
    0.41
    Act Density 0.726%

    No Known Activations