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

    Neuronpedia

    INDEX
    Explanations

    mixed content snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    도의
    -0.07
     располож
    -0.07
    .ins
    -0.06
     Auschwitz
    -0.06
     oldValue
    -0.06
    先生
    -0.06
    ['<{
    -0.06
    毕业
    -0.06
     XBOOLE
    -0.06
    امی
    -0.06
    POSITIVE LOGITS
    Virgin
    0.07
    梁
    0.06
     Podesta
    0.06
    Sand
    0.06
     lov
    0.06
     crafted
    0.06
    ówn
    0.06
     referees
    0.06
    textures
    0.06
     Thought
    0.06
    Act Density 0.000%

    No Known Activations