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

    Neuronpedia

    INDEX
    Explanations

    references to familial relationships and pronouns

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

    his + relation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     resourceCulture
    -0.51
    moduleId
    -0.42
    getItemId
    -0.40
     NSString
    -0.40
     believe
    -0.40
    MARC
    -0.39
    altezza
    -0.39
     Sac
    -0.39
     pulse
    -0.39
    きたいと思います
    -0.39
    POSITIVE LOGITS
    rungsseite
    0.52
    companied
    0.50
    ImageContext
    0.47
     moglie
    0.44
    ніципалі
    0.41
     nakalista
    0.40
     diikuti
    0.39
    mybatisplus
    0.39
    HideFlags
    0.39
     linkovi
    0.38
    Act Density 0.020%

    No Known Activations