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

    Neuronpedia

    INDEX
    Explanations

    Named entities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ители
    -0.07
    ไฟล
    -0.07
    Secret
    -0.06
    ている
    -0.06
     springfox
    -0.06
    Defined
    -0.06
    Sex
    -0.06
     acidic
    -0.06
     낮
    -0.06
     tiên
    -0.06
    POSITIVE LOGITS
     views
    0.07
     FAIL
    0.06
    'є
    0.06
     десяти
    0.06
    ~":"
    0.06
     involved
    0.06
    _Flag
    0.06
    (NULL
    0.06
    sandbox
    0.06
     prevalence
    0.06
    Act Density 0.009%

    No Known Activations