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

    Neuronpedia

    INDEX
    Explanations

    references to male individuals and their relationships

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

    pronoun followed by verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    olymers
    -0.43
    TagMode
    -0.43
    دانشنامهٔ
    -0.43
     COMPAT
    -0.43
    ValueStyle
    -0.42
    ellants
    -0.39
    complexContent
    -0.38
     Rising
    -0.38
     onBind
    -0.38
    hoedd
    -0.37
    POSITIVE LOGITS
     дописавши
    0.47
    :✨
    0.46
     HasFactory
    0.45
    antası
    0.43
    +#+#
    0.42
    íncipe
    0.39
    erçe
    0.39
     gesta
    0.38
     GenerationType
    0.38
    -------------</
    0.37
    Act Density 0.079%

    No Known Activations