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

    Neuronpedia

    INDEX
    Explanations

    expressions of reassurance or positive affirmations about well-being

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

    Statements of confirmation or agreement

    np_acts-logits-general · gemini-2.0-flash

    okay fine well normal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    قایناق‌لار
    -0.55
     дописавши
    -0.53
     mérite
    -0.53
    őle
    -0.52
    AddHtmlAttribute
    -0.51
     écl
    -0.51
     kasarigan
    -0.50
     Normdatei
    -0.49
    lccn
    -0.48
    Olvid
    -0.48
    POSITIVE LOGITS
     OK
    2.64
     okay
    2.59
     ok
    2.59
     alright
    2.20
    okay
    2.12
     Ok
    2.11
    OK
    2.10
    Ok
    2.06
     fine
    2.06
     OKAY
    2.04
    Act Density 0.195%

    No Known Activations