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

    Neuronpedia

    INDEX
    Explanations

    technical jargon related to electronics and digital systems.

    oai_token-act-pair · gemini-2.0-flash

    terms related to controllers

    np_token-act-pair-logits · gpt-4o-mini

    Circuit controllers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     незавершена
    -0.64
     ddelweddau
    -0.53
    oa̍t
    -0.53
    #+#
    -0.50
     Whis
    -0.48
     trajets
    -0.47
    NPS
    -0.47
     propOrder
    -0.47
     Audiodateien
    -0.47
    ỡng
    -0.47
    POSITIVE LOGITS
     controllers
    0.62
     Controllers
    0.59
    Controllers
    0.56
    AutoScaleMode
    0.56
     controller
    0.55
     IBOutlet
    0.53
    paq
    0.52
    LikeLike
    0.52
     circuit
    0.52
     Controller
    0.50
    Act Density 3.547%

    No Known Activations