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

    Neuronpedia

    INDEX
    Explanations

    characters and their relationships in the context of storytelling or narrative

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

    Names, often followed by verbs

    np_acts-logits-general · gemini-2.0-flash

    proper nouns used as character names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    setVerticalGroup
    -0.98
     autorytatywna
    -0.85
     betweenstory
    -0.77
    AndroidJUnit
    -0.76
     kasarigan
    -0.74
    )++;
    -0.74
    OGND
    -0.71
     بيها
    -0.71
     مشين
    -0.69
     للاسماء
    -0.67
    POSITIVE LOGITS
     himself
    0.89
     who
    0.84
     his
    0.79
    his
    0.76
    '
    0.73
    ’
    0.71
    who
    0.65
     Jr
    0.65
     whom
    0.64
    himself
    0.58
    Act Density 0.542%

    No Known Activations