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

    Neuronpedia

    INDEX
    Explanations

    indicators of engagement and interest in a subject

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

    Follows "response," "requested," or "received"

    np_acts-logits-general · gemini-2.0-flash

    response and received feedback

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gynhyrchwyd
    -0.63
    UserScript
    -0.63
     surla
    -0.59
    astéroïdes
    -0.58
     EconPapers
    -0.56
     InputDecoration
    -0.55
    GEBURTS
    -0.54
    GEBURTSDATUM
    -0.54
     ComVisible
    -0.53
    AlterField
    -0.53
    POSITIVE LOGITS
     eagerness
    0.36
     curiosity
    0.35
     response
    0.31
     zainteres
    0.31
    response
    0.30
     Interesse
    0.30
    nearly
    0.29
     ControllerBase
    0.29
     testimonials
    0.29
    月号
    0.29
    Act Density 0.237%

    No Known Activations