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

    Neuronpedia

    INDEX
    Explanations

    terms related to suitability and choice in various contexts

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

    Preceding words for adverbs that intensify or improve

    np_acts-logits-general · gemini-2.0-flash

    positive evaluation after a noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    出版年
    -0.60
    fromCharCode
    -0.45
     acordo
    -0.44
    esez
    -0.44
    AndEndTag
    -0.44
    FontOfSize
    -0.42
    godic
    -0.41
     obstante
    -0.41
     acuerdo
    -0.40
    пущен
    -0.40
    POSITIVE LOGITS
     better
    1.39
     perfectly
    1.22
     quite
    1.14
     much
    1.12
     greatly
    1.11
     very
    1.11
     admirably
    1.10
     immensely
    1.10
     tremendously
    1.09
    perfectly
    1.09
    Act Density 0.803%

    No Known Activations