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

    Neuronpedia

    INDEX
    Explanations

    boolean values representing states of conditions

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

    false followed by semicolon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     afterwards
    -0.31
    ,
    -0.30
     Universitaria
    -0.28
     whatever
    -0.27
    .
    -0.26
    )
    -0.26
     denen
    -0.25
     when
    -0.24
    whatever
    -0.23
     subsequently
    -0.23
    POSITIVE LOGITS
     مرئيه
    0.91
     Drapeau
    0.88
     False
    0.75
    extAlignment
    0.72
    SetBool
    0.71
     FALSE
    0.71
     beſte
    0.71
     $_(
    0.71
     queſta
    0.71
    ſchaft
    0.70
    Act Density 0.018%

    No Known Activations