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

    Neuronpedia

    INDEX
    Explanations

    *

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ��
    -0.07
    _spec
    -0.06
     SHIFT
    -0.06
     Uz
    -0.06
     zatím
    -0.06
     UIT
    -0.06
     Flower
    -0.06
     beers
    -0.06
    _R
    -0.06
     prostě
    -0.06
    POSITIVE LOGITS
    ed
    0.07
    ت
    0.07
    usable
    0.06
    (cond
    0.06
     TESTING
    0.06
     总
    0.06
     permanent
    0.06
    ود
    0.06
    random
    0.06
    (first
    0.06
    Act Density 0.001%

    No Known Activations