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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    필
    -0.08
     Newcastle
    -0.08
    งาน
    -0.08
     Calvin
    -0.07
    ေအ
    -0.07
     collection
    -0.07
     Sammlung
    -0.07
    collection
    -0.07
    -0.07
    อก
    -0.07
    POSITIVE LOGITS
     particularly
    0.08
     verfüg
    0.08
     ਗਿਆ
    0.08
     Pets
    0.08
     PROF
    0.08
     Figura
    0.08
     ਉਦ
    0.07
     مض
    0.07
     besonders
    0.07
     contemporary
    0.07
    Act Density 0.003%
    No Known Activations