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

    Neuronpedia

    INDEX
    Explanations

    Sex

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    geb
    -0.07
    ')?>
    -0.07
     设
    -0.07
     {}\
    -0.07
    	us
    -0.06
    �
    -0.06
    し�
    -0.06
     поб
    -0.06
     emulation
    -0.06
    orry
    -0.06
    POSITIVE LOGITS
    ＿＿＿＿＿＿＿＿
    0.06
    PART
    0.06
     FirstName
    0.06
    UserController
    0.06
    ightly
    0.06
     seemed
    0.06
    Localization
    0.06
     systematic
    0.06
    -logo
    0.06
     involuntary
    0.06
    Act Density 0.051%

    No Known Activations