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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and expressions related to variables and functions in scientific texts

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

    math symbols and structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     зак
    -0.33
     NSCoder
    -0.28
    AutoScale
    -0.27
    documentclass
    -0.27
    put
    -0.27
     Вікі
    -0.26
    C
    -0.26
     Cité
    -0.25
    )*
    -0.25
     enceinte
    -0.25
    POSITIVE LOGITS
    OGND
    0.74
    <unused79>
    0.70
    <unused28>
    0.70
    <unused51>
    0.70
    <unused16>
    0.70
    <unused8>
    0.70
    <unused41>
    0.70
    <unused43>
    0.70
    <unused74>
    0.70
    [@BOS@]
    0.69
    Act Density 0.134%

    No Known Activations