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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    해서
    -0.06
    pei
    -0.06
    /version
    -0.06
    .Required
    -0.06
    ость
    -0.06
     ř
    -0.06
    ẩ
    -0.06
     especific
    -0.06
     Herr
    -0.06
    ству
    -0.06
    POSITIVE LOGITS
    أن
    0.06
    告诉
    0.06
    _hdr
    0.06
     april
    0.06
     bev
    0.06
    _SECRET
    0.06
     Detroit
    0.06
    (setq
    0.06
    Tip
    0.06
    ijkl
    0.06
    Act Density 0.009%

    No Known Activations