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

    Neuronpedia

    INDEX
    Explanations

    data type definitions and variable declarations in programming code

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

    variable types with `leak` or `start`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.48
    EndContext
    -0.40
    ,
    -0.38
     doInBackground
    -0.34
     and
    -0.31
     esternos
    -0.30
    withstanding
    -0.29
     Töchter
    -0.28
     nämlich
    -0.28
     akong
    -0.28
    POSITIVE LOGITS
     Roskov
    0.75
     Normdatei
    0.73
    drawiam
    0.68
     propOrder
    0.64
     ſind
    0.63
    gsmål
    0.62
     müſſen
    0.59
     laſſen
    0.58
     Geiſt
    0.58
     geſch
    0.57
    Act Density 0.019%

    No Known Activations