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

    Neuronpedia

    INDEX
    Explanations

    specific numerical values and attributes related to character skills and powers

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

    Comes before articles or prepositions

    np_acts-logits-general · gemini-2.0-flash

    game attributes and abilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Exactos
    -0.74
     урна
    -0.66
    بوابة
    -0.66
    脚注の使い方
    -0.62
    MENAFN
    -0.62
    uterine
    -0.58
    ěry
    -0.54
    linearGradient
    -0.54
     promissory
    -0.52
     Lillie
    -0.51
    POSITIVE LOGITS
     defense
    0.82
     stats
    0.76
     stat
    0.75
     defence
    0.75
     defenses
    0.67
     agi
    0.65
     attack
    0.65
     strength
    0.64
     Defense
    0.63
     ModelExpression
    0.63
    Act Density 0.166%

    No Known Activations