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

    Neuronpedia

    INDEX
    Explanations

    Citations or references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Erick
    -0.08
     Cosmic
    -0.08
     CSC
    -0.07
     delt
    -0.07
    用人
    -0.07
     concede
    -0.07
     GR
    -0.07
    spy
    -0.07
     teşekkür
    -0.06
     Attempt
    -0.06
    POSITIVE LOGITS
     joint
    0.07
     bu
    0.07
    等多种
    0.07
    (public
    0.07
    0.07
     public
    0.07
    督促
    0.07
    消防安全
    0.06
    _io
    0.06
     --------------------------------------------------------------------------↵
    0.06
    Act Density 0.002%

    No Known Activations