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

    Neuronpedia

    INDEX
    Explanations

    Numerical data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    '])[
    -0.07
     inserting
    -0.06
    аться
    -0.06
     extractor
    -0.06
    까
    -0.06
     explicit
    -0.06
    细
    -0.06
     staffer
    -0.06
    .Matchers
    -0.06
    201
    -0.06
    POSITIVE LOGITS
     mug
    0.07
     geme
    0.07
     Lowe
    0.07
    _ble
    0.06
    _entry
    0.06
     midi
    0.06
     bluetooth
    0.06
    -mouth
    0.06
    θηκαν
    0.06
    .Dialog
    0.06
    Act Density 0.016%

    No Known Activations