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

    Neuronpedia

    INDEX
    Explanations

    descriptors related to aesthetics and style in various contexts

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

    ending in "ing," "ed," or similar suffixes

    np_acts-logits-general · gemini-2.0-flash

    describing appearance and style

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    出版年
    -0.58
    ThroughAttribute
    -0.52
    nościo
    -0.51
    SuppressLint
    -0.46
    arakhand
    -0.46
     الرياضيه
    -0.46
    NewUrlParser
    -0.45
     Roskov
    -0.45
     businessmen
    -0.44
    seamnă
    -0.44
    POSITIVE LOGITS
     accentuated
    0.41
     khuy
    0.41
    Зноскі
    0.39
    versy
    0.37
     aesthetic
    0.37
     nicer
    0.36
     nicely
    0.35
     contrasting
    0.35
     OMITBAD
    0.35
     Pic
    0.35
    Act Density 0.178%

    No Known Activations