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

    Neuronpedia

    INDEX
    Explanations

    negations and adjectives related to negativity or impossibility

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

    following "not only" (or similar phrases)

    np_acts-logits-general · gemini-2.0-flash

    not only, also, importantly, is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    zelfde
    -0.70
    tagHelperRunner
    -0.66
    VIAF
    -0.64
     समीक्षक
    -0.62
     Roskov
    -0.61
    ására
    -0.61
    AndroidJUnit
    -0.60
    liosis
    -0.60
     EconPapers
    -0.60
     senare
    -0.58
    POSITIVE LOGITS
     aesthetically
    0.75
     fun
    0.65
     FUN
    0.63
     Privacidade
    0.62
     delicious
    0.58
    FUN
    0.58
     aesthetic
    0.56
     beautiful
    0.55
    fun
    0.54
     profitable
    0.53
    Act Density 0.229%

    No Known Activations