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

    Neuronpedia

    INDEX
    Explanations

    bishop

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    太空
    -0.08
     }
    -0.07
    INED
    -0.07
    andalone
    -0.07
    unte
    -0.07
    渝
    -0.06
     Tyson
    -0.06
    ܛ
    -0.06
    ⵖ
    -0.06
     воздействи
    -0.06
    POSITIVE LOGITS
     bishop
    0.09
     Society
    0.07
     ns
    0.07
    믕
    0.07
    LENGTH
    0.07
     millis
    0.07
     sanction
    0.07
     canonical
    0.07
     papers
    0.07
     mec
    0.07
    Act Density 0.005%

    No Known Activations