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

    Neuronpedia

    INDEX
    Explanations

    successfully

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ्ल
    -0.07
    amment
    -0.07
    (prediction
    -0.07
    ủ
    -0.06
     tire
    -0.06
    ะแนน
    -0.06
    .slides
    -0.06
     presentations
    -0.06
     utilizar
    -0.06
    weights
    -0.06
    POSITIVE LOGITS
     AtomicInteger
    0.07
    _ASYNC
    0.07
     instal
    0.06
    뿐
    0.06
     doi
    0.06
    feit
    0.06
    (B
    0.06
    異
    0.06
     Assignment
    0.06
    735
    0.06
    Act Density 0.401%

    No Known Activations