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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mj
    -0.07
    -я
    -0.06
     男
    -0.06
    -be
    -0.06
     estrogen
    -0.06
     갤로그
    -0.06
    -thumb
    -0.06
    移到
    -0.06
    oday
    -0.06
     erotisch
    -0.06
    POSITIVE LOGITS
     personnel
    0.07
    Monitoring
    0.07
     Admission
    0.06
    UNS
    0.06
    公開
    0.06
    нист
    0.06
     перер
    0.06
     ARTICLE
    0.06
    ilibrium
    0.06
     DHS
    0.06
    Act Density 0.005%

    No Known Activations