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

    Neuronpedia

    INDEX
    Explanations

    references to custom-made or specially designed items and structures

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

    custom-made

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -0.84
     EconPapers
    -0.75
     kasarigan
    -0.59
    참고
    -0.59
    Tikang
    -0.57
    principalColumn
    -0.57
     FetchType
    -0.57
     فريبيس
    -0.56
    rungsseite
    -0.54
    Referències
    -0.51
    POSITIVE LOGITS
     tailored
    0.51
     tailor
    0.48
    Specialized
    0.48
     specialised
    0.47
    builtin
    0.45
     specialized
    0.45
     designed
    0.45
    designed
    0.44
     homemade
    0.42
     customized
    0.42
    Act Density 0.005%

    No Known Activations