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

    Neuronpedia

    INDEX
    Explanations

    commands related to loading and processing machine learning models

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

    Code, math, or device-related expressions

    np_acts-logits-general · gemini-2.0-flash

    torch, device, np, cu

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MessageTagHelper
    -0.50
    writeHead
    -0.47
     Dodson
    -0.46
     Beverley
    -0.46
     EconPapers
    -0.45
     Coleoptera
    -0.45
    odon
    -0.44
     Kef
    -0.43
     Magnolia
    -0.43
    AutoScaleMode
    -0.43
    POSITIVE LOGITS
     torch
    1.06
    torch
    0.92
     torches
    0.79
     MainAxisSize
    0.74
    :✨
    0.73
    Torch
    0.70
    MethodManager
    0.68
    WEBPACK
    0.68
     estekak
    0.65
    SharedCtor
    0.63
    Act Density 0.052%

    No Known Activations