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

    Neuronpedia

    INDEX
    Explanations

    technical descriptions related to processes and measurements in a scientific context

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

    Steps or processes being done

    np_acts-logits-general · gemini-2.0-flash

    processing treatments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     MainAxisSize
    -0.61
     GetEnumerator
    -0.60
     NSCoder
    -0.55
    +#+
    -0.51
    يميديا
    -0.49
     levantó
    -0.47
    ècie
    -0.47
    tinta
    -0.47
    ěli
    -0.46
     (;;)
    -0.46
    POSITIVE LOGITS
     processing
    0.90
    transform
    0.82
     process
    0.80
     Processing
    0.78
     transform
    0.74
    processing
    0.74
     transformation
    0.74
     processes
    0.73
    Processing
    0.73
     transformations
    0.72
    Act Density 1.040%

    No Known Activations