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

    Neuronpedia

    INDEX
    Explanations

    's

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     serr
    -0.07
     ряд
    -0.07
    全局
    -0.07
     halt
    -0.07
     relax
    -0.07
     informational
    -0.07
     park
    -0.07
    -private
    -0.06
    Interpolator
    -0.06
    HH
    -0.06
    POSITIVE LOGITS
    挥
    0.07
    antium
    0.06
     تلك
    0.06
    [mid
    0.06
     pelos
    0.06
     Already
    0.06
    _First
    0.06
     joining
    0.06
     müşter
    0.06
     "[%
    0.06
    Act Density 0.002%

    No Known Activations