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

    Neuronpedia

    INDEX
    Explanations

    computing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    窝
    -0.07
     gem
    -0.07
    fine
    -0.07
    ｄ
    -0.07
    “If
    -0.06
    宾
    -0.06
    دور
    -0.06
    'label
    -0.06
    “He
    -0.06
    ark
    -0.06
    POSITIVE LOGITS
    .by
    0.08
    药师
    0.07
     Conserv
    0.07
    给了我
    0.07
    🏉
    0.07
    ⊹
    0.07
     slender
    0.07
    Ỷ
    0.07
    CustomLabel
    0.07
    (Utils
    0.07
    Act Density 0.158%

    No Known Activations