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

    Neuronpedia

    INDEX
    Explanations

    use

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     año
    -0.07
     rng
    -0.07
     broadcasting
    -0.07
    ียน
    -0.06
     �
    -0.06
     obsessive
    -0.06
     FOREIGN
    -0.06
    faq
    -0.06
     revealed
    -0.06
     coming
    -0.06
    POSITIVE LOGITS
    _check
    0.07
    .SetText
    0.06
     خوان
    0.06
     IPV
    0.06
     refute
    0.06
    -upload
    0.06
     هم
    0.06
    _deposit
    0.06
    Invoke
    0.06
    .expect
    0.06
    Act Density 0.002%

    No Known Activations