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

    Neuronpedia

    INDEX
    Explanations

    references to bowling actions and performance statistics

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

    user or <start_of_turn>

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Fast
    -0.38
    tagHelper
    -0.38
     Fast
    -0.37
     metų
    -0.34
     grill
    -0.34
     įsi
    -0.33
     galería
    -0.33
     MMP
    -0.33
    +#+
    -0.32
     nélk
    -0.32
    POSITIVE LOGITS
     spinning
    0.83
     spinners
    0.77
    spinning
    0.73
     spin
    0.71
     Spin
    0.70
     spins
    0.70
    Spinning
    0.69
    Spinner
    0.69
     spinner
    0.69
     spun
    0.66
    Act Density 0.027%

    No Known Activations