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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks or commas

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

    when a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    べく
    -0.41
     for
    -0.34
      
    -0.33
    ようで
    -0.33
    {},
    -0.33
    reichen
    -0.33
     Despite
    -0.33
    ↵↵
    -0.32
     of
    -0.32
     Robert
    -0.31
    POSITIVE LOGITS
    :✨
    0.85
     wireType
    0.82
    Хьажоргаш
    0.78
     المعيارى
    0.76
    tagHelperRunner
    0.76
    principalColumn
    0.75
     Roskov
    0.74
     للمعارف
    0.73
     Administrativna
    0.71
     feroit
    0.70
    Act Density 0.072%

    No Known Activations