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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate provision, demonstration, and causation

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

    causes or enables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     capaz
    -0.41
    WebServlet
    -0.39
    mampuan
    -0.38
    izante
    -0.36
     elettrica
    -0.36
     numériques
    -0.36
    struzione
    -0.36
     sukker
    -0.35
    amom
    -0.35
     Audiodateien
    -0.35
    POSITIVE LOGITS
     pinulongan
    0.68
     NSCoder
    0.60
     gyhoeddwyd
    0.54
    tanleria
    0.53
    GeneratedCode
    0.53
    دانشنامهٔ
    0.50
    InputBorder
    0.50
     sumpay
    0.50
    Tikang
    0.50
     noDo
    0.49
    Act Density 0.249%

    No Known Activations