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

    Neuronpedia

    INDEX
    Explanations

    rows and columns

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    去找
    -0.07
    出处
    -0.07
     throwable
    -0.07
    ﺰ
    -0.07
    distribution
    -0.07
     transporting
    -0.06
     Image
    -0.06
    万亩
    -0.06
    스
    -0.06
     criticize
    -0.06
    POSITIVE LOGITS
    Req
    0.07
     التق
    0.07
     RP
    0.07
     prv
    0.07
    _locked
    0.07
    Ճ
    0.07
    /close
    0.07
    ('/')[
    0.07
    грани
    0.07
    igans
    0.07
    Act Density 0.023%

    No Known Activations