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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Yog
    -0.06
     cid
    -0.06
    υγ
    -0.06
     Rog
    -0.06
    forcement
    -0.06
     chatt
    -0.06
     monitoring
    -0.06
     Eld
    -0.06
    _upgrade
    -0.06
    руч
    -0.06
    POSITIVE LOGITS
    -notch
    0.06
     rencontrer
    0.06
     }));↵
    0.06
     trades
    0.06
     mListener
    0.06
    igrant
    0.06
    prend
    0.06
    Associated
    0.06
    無し
    0.06
     disturbed
    0.06
    Act Density 0.250%

    No Known Activations