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

    Neuronpedia

    INDEX
    Explanations

    the term "dead" in various contexts

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

    "dead" and related contexts

    np_acts-logits-general · gemini-2.0-flash

    deadlock

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tocin
    -0.67
     pinulongan
    -0.66
     estekak
    -0.59
    Portale
    -0.57
     Lari
    -0.57
     незавершена
    -0.56
     UIKit
    -0.55
    jsoup
    -0.54
    Portail
    -0.53
     Lui
    -0.53
    POSITIVE LOGITS
     dead
    0.92
     Dead
    0.90
    Dead
    0.89
    dead
    0.80
     DEAD
    0.79
    beats
    0.77
    beat
    0.75
    DEAD
    0.73
    Beats
    0.68
    icated
    0.67
    Act Density 0.037%

    No Known Activations