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

    Neuronpedia

    INDEX
    Explanations

    For

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cuisine
    -0.07
    BMI
    -0.06
    ertest
    -0.06
     буд
    -0.06
    'label
    -0.06
     Dum
    -0.06
    (isinstance
    -0.06
     rost
    -0.06
    ificance
    -0.06
    aney
    -0.06
    POSITIVE LOGITS
     Fr
    0.07
    -year
    0.07
     German
    0.06
    hon
    0.06
    Fr
    0.06
     Jeremy
    0.06
     tutorial
    0.06
     vài
    0.06
     lety
    0.06
     ниже
    0.06
    Act Density 0.019%

    No Known Activations