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

    Neuronpedia

    INDEX
    Explanations

    unicode characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ("(
    -0.07
     Tre
    -0.07
    ugh
    -0.06
    徼
    -0.06
     augmentation
    -0.06
    HG
    -0.06
     driven
    -0.06
     ›
    -0.06
    ign
    -0.06
     inflammation
    -0.06
    POSITIVE LOGITS
     FUNCTIONS
    0.07
    rzy
    0.07
    .contact
    0.07
     تصنيف
    0.07
    _repr
    0.07
     כניס
    0.07
     реализаци
    0.07
    utow
    0.07
     )↵↵
    0.07
    :)↵
    0.07
    Act Density 0.005%

    No Known Activations