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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     adel
    -0.06
     Payment
    -0.06
     USERS
    -0.06
     anlaş
    -0.06
     Plains
    -0.06
    되어
    -0.06
    ->{'
    -0.06
     Orn
    -0.06
    /cloud
    -0.06
    -cost
    -0.05
    POSITIVE LOGITS
     posed
    0.07
    manufacturer
    0.06
    gt
    0.06
    ')),
    0.06
     with
    0.06
     خودش
    0.06
    unds
    0.06
     quantitative
    0.06
    _generator
    0.06
    .At
    0.06
    Act Density 0.006%

    No Known Activations