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

    Neuronpedia

    INDEX
    Explanations

    references to files and technical terms related to data processing

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

    patch files and commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surla
    -0.47
    verwijspagina
    -0.43
    DoubleQuotes
    -0.43
    uação
    -0.40
     metav
    -0.39
    ChildScrollView
    -0.39
    XmlAccessType
    -0.39
    ilija
    -0.38
    atguigu
    -0.38
    viewBox
    -0.37
    POSITIVE LOGITS
     patch
    1.78
    patch
    1.73
     Patch
    1.73
    Patch
    1.69
     patches
    1.69
     PATCH
    1.60
     patching
    1.57
     Patches
    1.50
    PATCH
    1.45
     patched
    1.41
    Act Density 0.013%

    No Known Activations