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

    Neuronpedia

    INDEX
    Explanations

    emotional expressions and reflections on personal experiences

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

    Follows punctuation or "know"

    np_acts-logits-general · gemini-2.0-flash

    remembering past events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tonode
    -0.39
    HtmlAttribute
    -0.38
     Gef
    -0.36
    inSlope
    -0.35
    ItemBackground
    -0.34
     deler
    -0.32
     interestingly
    -0.31
     Ges
    -0.31
    Ljava
    -0.31
     Dar
    -0.30
    POSITIVE LOGITS
    Tembelea
    0.63
    先是
    0.63
     aside
    0.60
    まず
    0.54
     <<<<<<<<<<<<<<
    0.52
    iyor
    0.51
    Portail
    0.51
     polega
    0.50
    不僅
    0.49
     außer
    0.49
    Act Density 0.350%

    No Known Activations