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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, specifically names of individuals

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

    classic male celebrity names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    jdt
    -0.47
    存于互联网档案馆
    -0.44
    /**
    -0.44
    ']))
    -0.43
    łbym
    -0.42
     useRef
    -0.42
    isEqualTo
    -0.40
    '])){
    -0.39
    xsl
    -0.38
    }\|
    -0.38
    POSITIVE LOGITS
     Frankie
    1.15
     Richie
    1.07
    Frankie
    1.02
     Rosie
    0.96
     Bernie
    0.96
    Richie
    0.95
     Louie
    0.94
     Nicky
    0.94
     Benny
    0.93
     Angie
    0.91
    Act Density 0.006%

    No Known Activations