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

    Neuronpedia

    INDEX
    Explanations

    geographical references and locations

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

    from or representing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    avimas
    -0.33
    __((
    -0.32
    rrggbb
    -0.31
    
    -0.30
    ::_('
    -0.29
     tick
    -0.29
     doigts
    -0.28
    Acab
    -0.28
    เส
    -0.28
    ModuleName
    -0.28
    POSITIVE LOGITS
    chymal
    0.66
     verteilt
    0.63
    ConstraintMaker
    0.60
    ScopeManager
    0.60
     various
    0.59
     çeşitli
    0.58
     verspre
    0.58
    various
    0.58
     distributed
    0.57
     Wikimedijinoj
    0.57
    Act Density 0.024%

    No Known Activations