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

    Neuronpedia

    INDEX
    Explanations

    references to athletic competitions and achievements

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

    before numbers

    np_acts-logits-general · gemini-2.0-flash

    dynamic / for catalysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /******/
    -0.64
    asymp
    -0.58
    seamnă
    -0.57
     Ceramby
    -0.57
     attent
    -0.56
    PMG
    -0.55
    ٪
    -0.54
    tldr
    -0.53
     createState
    -0.51
     Puck
    -0.51
    POSITIVE LOGITS
    MessageOf
    0.63
     coach
    0.60
    UnusedPrivate
    0.60
     Coach
    0.56
    ostante
    0.56
     skipper
    0.55
    Coach
    0.55
    DeleteBehavior
    0.54
    Obrázky
    0.53
    AndEndTag
    0.52
    Act Density 0.064%

    No Known Activations