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

    Neuronpedia

    INDEX
    Explanations

    Dilemmas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tennis
    -0.07
    .lucene
    -0.07
     transformations
    -0.06
     partir
    -0.06
     Rails
    -0.06
     Detect
    -0.06
     marches
    -0.06
    apos
    -0.06
    什么
    -0.06
    .addValue
    -0.06
    POSITIVE LOGITS
    胸
    0.07
     информа
    0.07
     وم
    0.06
     adına
    0.06
     pozisyon
    0.06
    도가
    0.06
    ´:
    0.06
     О
    0.06
    ครบ
    0.06
    shipping
    0.06
    Act Density 0.261%

    No Known Activations