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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names of individuals

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

    Famous people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wife
    -0.75
    Husband
    -0.74
     Wife
    -0.71
     husband
    -0.70
    TargetException
    -0.69
     spouses
    -0.69
    husband
    -0.68
    Wife
    -0.67
     wives
    -0.67
     husbands
    -0.67
    POSITIVE LOGITS
     Photocase
    0.45
    Rhestr
    0.39
     Stab
    0.35
     Pens
    0.35
     Finn
    0.34
    topLeft
    0.33
     artists
    0.33
     aco
    0.32
     समीक्षाओं
    0.31
     FEED
    0.31
    Act Density 0.050%

    No Known Activations