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

    Neuronpedia

    INDEX
    Explanations

    unique punctuation marks and specific symbols

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

    punctuation and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     extranjero
    -0.48
     başladı
    -0.44
     başlad
    -0.42
     extranjera
    -0.41
     convivencia
    -0.41
     Spitze
    -0.39
     potentially
    -0.36
     asiatique
    -0.36
     doloroso
    -0.36
     prohibido
    -0.36
    POSITIVE LOGITS
     otomatig
    0.76
    tagHelperRunner
    0.73
    TestBed
    0.67
    enumii
    0.60
    ConstraintMaker
    0.60
    URLException
    0.59
     ujednoznacz
    0.58
    expandindo
    0.57
    PreferredItem
    0.56
    rungsseite
    0.56
    Act Density 0.003%

    No Known Activations