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

    Neuronpedia

    INDEX
    Explanations

    statements related to seeking information or guidance

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

    First-person pronouns and related words

    np_acts-logits-general · gemini-2.0-flash

    my, I, and possessive pronouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.59
    ponses
    -0.56
     Мексичка
    -0.55
    -0.54
     nonatomic
    -0.51
     CreateTagHelper
    -0.50
     Савезне
    -0.48
    ₂+
    -0.47
     deepest
    -0.47
    argu
    -0.47
    POSITIVE LOGITS
     my
    0.89
    my
    0.72
     mogę
    0.64
     minhas
    0.63
     I
    0.63
     mijn
    0.63
     meine
    0.62
     myself
    0.61
    Przypisy
    0.61
     моих
    0.61
    Act Density 0.121%

    No Known Activations