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

    Neuronpedia

    INDEX
    Explanations

    numbers and units

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     minden
    -0.07
    Integer
    -0.07
     calculus
    -0.07
    _maximum
    -0.07
    たち
    -0.06
     Automatically
    -0.06
    .setTextColor
    -0.06
    Cette
    -0.06
     weaponry
    -0.06
    archy
    -0.06
    POSITIVE LOGITS
    베
    0.07
    แข
    0.06
    722
    0.06
    KL
    0.06
    $db
    0.06
     Honda
    0.06
     Point
    0.06
    bands
    0.06
     benchmark
    0.06
     Pepsi
    0.06
    Act Density 0.029%

    No Known Activations