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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate topics of information or inquiry

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

    information about

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    EndContext
    -0.73
    Personensuche
    -0.68
    AddTagHelper
    -0.67
    цездатний
    -0.67
     <<<<<<<<<<<<<<
    -0.66
    fromnode
    -0.66
     resourceCulture
    -0.65
     CURIAM
    -0.65
    UnusedPrivate
    -0.64
    yntaxException
    -0.64
    POSITIVE LOGITS
     about
    0.45
     quels
    0.41
     ABOUT
    0.40
    เกี่ยวกับ
    0.39
     regarding
    0.37
     miten
    0.37
    ┃
    0.37
    วันที่
    0.37
     cette
    0.36
     concerning
    0.36
    Act Density 0.005%

    No Known Activations