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

    Neuronpedia

    INDEX
    Explanations

    scientific studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     leth
    -0.07
     Athens
    -0.06
    ेखन
    -0.06
    (%
    -0.06
    Italic
    -0.06
    리에
    -0.06
    _base
    -0.06
    Rua
    -0.06
     Ala
    -0.06
     Rahman
    -0.06
    POSITIVE LOGITS
     vd
    0.07
     turbo
    0.06
     resistor
    0.06
    dogs
    0.06
     Lum
    0.06
    ::*;↵
    0.06
     robust
    0.06
    _heads
    0.06
     Kaplan
    0.06
    cant
    0.06
    Act Density 0.362%

    No Known Activations