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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     recipes
    -0.07
     cigarettes
    -0.06
    ;/
    -0.06
    .sax
    -0.06
    _CLASS
    -0.06
     licking
    -0.06
    .ws
    -0.06
     свя
    -0.06
     K
    -0.06
     routes
    -0.06
    POSITIVE LOGITS
     glUniform
    0.07
     entender
    0.07
    _inactive
    0.07
    Před
    0.07
    準
    0.06
    ابه
    0.06
    ▏
    0.06
     Barb
    0.06
    最高
    0.06
    horizontal
    0.06
    Act Density 0.213%

    No Known Activations