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

    Neuronpedia

    INDEX
    Explanations

    units

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chạy
    -0.07
     němu
    -0.07
     čtyř
    -0.06
     hunted
    -0.06
    Props
    -0.06
    tar
    -0.06
    賀
    -0.06
     Hunts
    -0.06
     Tos
    -0.06
    šlo
    -0.06
    POSITIVE LOGITS
     Beta
    0.08
    规划
    0.06
     hoses
    0.06
     basın
    0.06
     Advocate
    0.06
    (cluster
    0.06
     Muse
    0.06
    _decimal
    0.06
    GEST
    0.06
    straints
    0.06
    Act Density 0.001%

    No Known Activations