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

    Neuronpedia

    INDEX
    Explanations

    tell

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Paras
    -0.07
     fw
    -0.07
     пери
    -0.06
     Comparative
    -0.06
    Під
    -0.06
     passes
    -0.06
     pollen
    -0.06
     Slam
    -0.06
    互
    -0.06
    _TAG
    -0.06
    POSITIVE LOGITS
     cereal
    0.07
    SPORT
    0.06
    _vectors
    0.06
     cannabis
    0.06
    ’S
    0.06
    andas
    0.06
     compel
    0.06
    Formatting
    0.06
    อน
    0.06
     likelihood
    0.06
    Act Density 0.002%

    No Known Activations