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

    Neuronpedia

    INDEX
    Explanations

    phrases related to data analysis and performance metrics

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

    Comparison or exceeding expectations

    np_acts-logits-general · gemini-2.0-flash

    exceeds surpasses outweighs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dAtA
    -0.58
    FunctionFlags
    -0.56
    delwed
    -0.53
     Winaray
    -0.53
     useCallback
    -0.52
    akterysty
    -0.50
    خصة
    -0.49
    RenderAtEndOf
    -0.49
    Enllaces
    -0.49
    rungsseite
    -0.46
    POSITIVE LOGITS
     surpass
    1.79
     surpassed
    1.74
     beat
    1.69
     surpasses
    1.66
     surpassing
    1.55
     beats
    1.54
     exceed
    1.50
     exceeded
    1.45
     exceeds
    1.44
     beating
    1.37
    Act Density 0.497%

    No Known Activations