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
     scrib
    -0.09
     Necklace
    -0.09
     acuerdos
    -0.09
    ainted
    -0.09
     Jaguars
    -0.08
     Mitar
    -0.08
     spruce
    -0.08
    Margin
    -0.08
    963
    -0.08
     Lehrer
    -0.08
    POSITIVE LOGITS
    世界
    0.13
     society
    0.12
     दुनिया
    0.12
    生活
    0.12
     العالم
    0.11
     દુન
    0.11
     düny
    0.11
     duniya
    0.11
     samenleving
    0.11
     زندگی
    0.11
    Act Density 0.153%

    No Known Activations