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

    Neuronpedia

    INDEX
    Explanations

    legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    coordinates
    -0.08
     Stop
    -0.06
     breaking
    -0.06
    воля
    -0.06
     Bru
    -0.06
     Parr
    -0.06
     strip
    -0.05
     shocking
    -0.05
    逸
    -0.05
    .ArgumentParser
    -0.05
    POSITIVE LOGITS
    (..
    0.09
    =$((
    0.07
    บอก
    0.07
    *>(
    0.07
    _blend
    0.06
     *>(
    0.06
    (pin
    0.06
     Agency
    0.06
     Александр
    0.06
    foregroundColor
    0.06
    Act Density 0.029%

    No Known Activations