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

    Neuronpedia

    INDEX
    Explanations

    Python code syntax

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ตร
    -0.09
     Temperature
    -0.08
     Tr
    -0.08
     P
    -0.07
     Rid
    -0.07
     ενδια
    -0.07
     temperature
    -0.07
     사람들이
    -0.07
     방문
    -0.07
     flips
    -0.07
    POSITIVE LOGITS
    special
    0.08
     раскры
    0.08
    rema
    0.08
     arre
    0.08
     special
    0.08
    enabled
    0.08
     bary
    0.08
    .special
    0.08
     cov
    0.07
    Coe
    0.07
    Act Density 0.003%

    No Known Activations