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

    Neuronpedia

    INDEX
    Explanations

    código

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     từ
    -0.07
     enquiry
    -0.06
     thé
    -0.06
    _weather
    -0.06
    	settings
    -0.06
    छ
    -0.06
     merge
    -0.06
    퇴
    -0.06
     emergence
    -0.06
    疗
    -0.06
    POSITIVE LOGITS
     Cincinnati
    0.08
     Diego
    0.07
    ęd
    0.07
     Chili
    0.07
     Occupy
    0.07
    .codigo
    0.07
    -wise
    0.07
     Rodriguez
    0.07
     Innoc
    0.07
     Duplicate
    0.07
    Act Density 0.009%

    No Known Activations