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

    Neuronpedia

    INDEX
    Explanations

    regulated

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    issen
    -0.08
    irmware
    -0.07
     van
    -0.07
     biking
    -0.07
    售
    -0.07
     Of
    -0.07
    מלך
    -0.07
    BER
    -0.07
    TO
    -0.07
     Rowe
    -0.07
    POSITIVE LOGITS
    实用
    0.07
    찾
    0.07
    司法
    0.06
    檔案
    0.06
     adaptations
    0.06
     nadzie
    0.06
     предназ
    0.06
    נטר
    0.06
     markup
    0.06
    	Description
    0.06
    Act Density 0.207%

    No Known Activations