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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     supply
    -0.07
     Broadcasting
    -0.07
     думку
    -0.07
    셔
    -0.06
     directly
    -0.06
    (@
    -0.06
    olicy
    -0.06
    几个
    -0.06
     діє
    -0.06
     ETF
    -0.06
    POSITIVE LOGITS
    USD
    0.07
     Pods
    0.06
     crown
    0.06
     ');↵
    0.06
     hospitalized
    0.06
     continua
    0.06
    洛
    0.06
     Rising
    0.06
    Activate
    0.06
    clamp
    0.06
    Act Density 0.087%

    No Known Activations