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

    Neuronpedia

    INDEX
    Explanations

    expressions of apology and regret

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

    Following personal pronouns or "to" and a verb

    np_acts-logits-general · gemini-2.0-flash

    posting replies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddressBook
    -0.56
    収録曲
    -0.51
    دانشنامهٔ
    -0.51
    UMBUS
    -0.46
    Mnemonic
    -0.45
    okus
    -0.45
    さえ
    -0.44
    源
    -0.44
    rxjs
    -0.43
    取材
    -0.43
    POSITIVE LOGITS
     posting
    1.33
     posts
    1.18
     Posting
    1.09
     postings
    1.08
     replies
    1.06
     replying
    1.06
    posting
    1.05
     moderators
    1.03
     posted
    1.02
    Posting
    1.00
    Act Density 0.464%

    No Known Activations