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

    Neuronpedia

    INDEX
    Explanations

    expressed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     peri
    -0.07
    ával
    -0.06
     Мари
    -0.06
    :Is
    -0.06
    inus
    -0.06
    _funcs
    -0.06
    AXB
    -0.06
     Lanka
    -0.06
     youngsters
    -0.06
     Zealand
    -0.06
    POSITIVE LOGITS
    ��
    0.07
     gratitude
    0.06
     Signup
    0.06
     первую
    0.06
    指
    0.06
    nde
    0.06
    وفي
    0.06
    수
    0.06
    .cf
    0.06
    ोई
    0.06
    Act Density 1.179%

    No Known Activations