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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and expressions

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

    mathematical code and diagrams

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nande
    -0.35
     Verbrechen
    -0.32
    nung
    -0.32
     ış
    -0.32
     prø
    -0.31
    ins
    -0.31
    itación
    -0.31
     ámbitos
    -0.31
    kmale
    -0.31
     rând
    -0.30
    POSITIVE LOGITS
     AssemblyTitle
    0.68
    +#+
    0.63
     CreateTagHelper
    0.57
     سكانية
    0.57
     Picchu
    0.56
    RectangleBorder
    0.56
    LayoutStyle
    0.55
     BoxDecoration
    0.55
    .*")]
    0.55
     كومونز
    0.54
    Act Density 0.345%

    No Known Activations