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

    Neuronpedia

    INDEX
    Explanations

    crime

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _AspNet
    -0.07
    ウィ
    -0.07
    racak
    -0.07
    重点
    -0.06
    ně
    -0.06
    овий
    -0.06
    IClient
    -0.06
     Istanbul
    -0.06
    альное
    -0.06
    expects
    -0.06
    POSITIVE LOGITS
     format
    0.06
    	Runtime
    0.06
     due
    0.06
     муницип
    0.06
    .hh
    0.06
    /about
    0.06
    api
    0.06
     schooling
    0.06
    olare
    0.06
    خة
    0.06
    Act Density 0.003%

    No Known Activations