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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     terug
    -0.06
    tingham
    -0.06
    connexion
    -0.06
     щоб
    -0.06
     환산
    -0.06
     استخدام
    -0.06
     tiếp
    -0.06
    etcode
    -0.06
     dovol
    -0.06
    َب
    -0.06
    POSITIVE LOGITS
     Pur
    0.08
     removeFrom
    0.07
     awaiting
    0.07
     waters
    0.07
     from
    0.07
     priv
    0.07
    urally
    0.07
    -from
    0.07
    _most
    0.07
    (from
    0.06
    Act Density 0.024%

    No Known Activations