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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or hypothetical situations

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

    replacement and substitution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     distributed
    -0.38
     Distributed
    -0.35
     рассе
    -0.34
     dağı
    -0.33
     autos
    -0.31
     CreateTagHelper
    -0.31
     disseminated
    -0.30
    Попис
    -0.30
    encre
    -0.30
     παρά
    -0.30
    POSITIVE LOGITS
     iconLine
    0.61
     replace
    0.60
     replacement
    0.59
     replacing
    0.59
    replacement
    0.58
     Replacement
    0.57
     replacements
    0.57
    Havolalar
    0.56
    uxxxx
    0.56
     replaced
    0.55
    Act Density 0.103%

    No Known Activations