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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and expressions related to functions and variables

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

    Greek letters and math symbols

    np_acts-logits-general · gemini-2.0-flash

    greek letters and mathematical symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Harris
    -0.77
     Janice
    -0.72
    Harris
    -0.68
     Levin
    -0.67
     Hogg
    -0.67
     Leith
    -0.66
     Yaz
    -0.63
    Janice
    -0.63
    姜
    -0.62
     Milo
    -0.61
    POSITIVE LOGITS
     autorytatywna
    0.72
     }_{\
    0.72
    _{\
    0.71
     Seok
    0.69
    }_{\
    0.68
     المعيارى
    0.68
     ujednoznacz
    0.67
    \|_{\
    0.67
     ASA
    0.67
     Kem
    0.67
    Act Density 1.370%

    No Known Activations