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

    Neuronpedia

    INDEX
    Explanations

    references to scoring and goals in sports contexts

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

    scored points or goals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     uParam
    -0.52
    netti
    -0.50
     Linden
    -0.50
     WIP
    -0.49
     distrust
    -0.48
     VM
    -0.47
     hindsight
    -0.47
     I
    -0.46
     Mam
    -0.45
     reluctance
    -0.45
    POSITIVE LOGITS
    AddTagHelper
    0.63
     NSCoder
    0.62
    ReusableCell
    0.58
    scoring
    0.57
    scored
    0.54
     мәкал
    0.51
     scoring
    0.50
     scored
    0.50
     leveren
    0.49
    sphin
    0.48
    Act Density 0.007%

    No Known Activations