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

    Neuronpedia

    INDEX
    Explanations

    comments and instructions related to implementing and converting code

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

    TODOs and auxiliary verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.35
     виправивши
    -0.34
    centralwidget
    -0.33
    appcompat
    -0.29
    Bibliograf
    -0.28
     douane
    -0.27
    სქოლიო
    -0.26
    verwijspagina
    -0.26
     rés
    -0.26
    Trusted
    -0.25
    POSITIVE LOGITS
    PerformLayout
    0.64
    antası
    0.61
     Infórmanos
    0.61
    fromnode
    0.60
    GEBURTS
    0.58
    ſelben
    0.57
     ModelExpression
    0.56
    :✨
    0.56
    ஂ
    0.55
    pgterms
    0.54
    Act Density 0.009%

    No Known Activations