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

    Neuronpedia

    INDEX
    Explanations

    3

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    wner
    -0.09
     Governments
    -0.07
    Pool
    -0.07
     fears
    -0.06
     ging
    -0.06
    НА
    -0.06
    际
    -0.06
     exploit
    -0.06
    格式
    -0.06
     англ
    -0.06
    POSITIVE LOGITS
    –and
    0.07
    $rs
    0.06
    _major
    0.06
    (handle
    0.06
    ⟩
    0.06
    �니다
    0.06
    PathVariable
    0.06
    _until
    0.06
    .Excel
    0.06
    (coeffs
    0.06
    Act Density 0.004%

    No Known Activations