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

    Neuronpedia

    INDEX
    Explanations

    adverbs that express degrees of ease or difficulty

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

    Adverbs modifying verbs

    np_acts-logits-general · gemini-2.0-flash

    easily or fully + verb/adjective/determiner

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     very
    -0.67
     Miquel
    -0.64
    Very
    -0.61
     really
    -0.60
     zelo
    -0.60
    very
    -0.59
     nagyon
    -0.56
    jima
    -0.56
    Очень
    -0.56
     extremely
    -0.55
    POSITIVE LOGITS
     unknownFields
    0.82
     تضيفلها
    0.76
    تقاوى
    0.74
     utafitiHapana
    0.74
    ValueStyle
    0.74
    ScopeManager
    0.70
    WriteBarrier
    0.70
    #+#
    0.69
    ymce
    0.68
     GetEnumerator
    0.64
    Act Density 0.234%

    No Known Activations