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

    Neuronpedia

    INDEX
    Explanations

    references to personal belongings and familial connections

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

    Possessive pronouns followed by location

    np_acts-logits-general · gemini-2.0-flash

    personal places and origins

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SharedDtor
    -0.69
     الحره
    -0.68
    UserScript
    -0.62
     Administrativna
    -0.62
    addCriterion
    -0.59
     validamos
    -0.56
     للاسماء
    -0.56
     صوتيه
    -0.56
    HideFlags
    -0.55
    iprot
    -0.54
    POSITIVE LOGITS
     home
    0.98
     hometown
    0.92
     hjem
    0.82
     homeland
    0.77
    home
    0.76
     native
    0.76
     hjemme
    0.74
    adopted
    0.73
     gebo
    0.70
     domov
    0.69
    Act Density 0.201%

    No Known Activations