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

    Neuronpedia

    INDEX
    Explanations

    technical terminology related to network and programming concepts

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

    programming code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kyse
    -0.35
    zulegen
    -0.35
     Untersuch
    -0.34
     hipó
    -0.31
    ">—
    -0.30
    (__('
    -0.29
     stø
    -0.29
     Verbre
    -0.29
    channelId
    -0.29
     éstas
    -0.28
    POSITIVE LOGITS
    GEBURTSDATUM
    0.76
    UserScript
    0.66
     CURIAM
    0.66
    transQ
    0.57
    WriteBarrier
    0.53
     disambiguazione
    0.52
    RTSN
    0.52
    tangentMode
    0.50
    addCriterion
    0.50
    stdc
    0.50
    Act Density 0.041%

    No Known Activations