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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and specific names, particularly related to places and people

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

    Capitalized words, often names or places

    np_acts-logits-general · gemini-2.0-flash

    place names and specific entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     
    -0.75
     (
    -0.64
    onViewCreated
    -0.63
      
    -0.61
    :
    -0.58
    setVerticalGroup
    -0.58
     single
    -0.57
    ngOnInit
    -0.57
    didSet
    -0.57
    ,
    -0.56
    POSITIVE LOGITS
    ſelf
    1.24
     Anſ
    1.20
    ſelves
    1.18
     ་་
    1.10
     Majefty
    1.08
     Houſe
    1.06
     Jefus
    1.06
     Diſ
    1.03
     ſind
    1.00
     Conſ
    0.96
    Act Density 0.565%

    No Known Activations