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

    Neuronpedia

    INDEX
    Explanations

    both

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nearly
    -0.07
     talking
    -0.07
     unlawful
    -0.06
     datas
    -0.06
     derivative
    -0.06
     hinted
    -0.06
     biggest
    -0.06
    (params
    -0.06
     он
    -0.06
     widespread
    -0.06
    POSITIVE LOGITS
     حفظ
    0.07
    认识
    0.07
     Adoption
    0.07
     растений
    0.06
     Female
    0.06
    _pdu
    0.06
     endure
    0.06
    oueur
    0.06
     کمتر
    0.06
    ()?>
    0.06
    Act Density 0.037%

    No Known Activations