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

    Neuronpedia

    INDEX
    Explanations

    pronouns he she

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ụy
    -0.07
     év
    -0.06
    Με
    -0.06
     leider
    -0.06
    ,on
    -0.06
    ندر
    -0.06
    NI
    -0.06
     pró
    -0.06
     spolupráci
    -0.06
     parece
    -0.06
    POSITIVE LOGITS
    .↵↵↵↵↵↵
    0.06
    (){}↵↵
    0.06
    ocoa
    0.06
    )&&
    0.06
     StatusCode
    0.06
    	↵	↵	↵	↵
    0.06
    ↵↵↵↵
    0.06
    //
↵
↵
    0.06
     "↵↵
    0.06
    //↵
    0.06
    Act Density 0.105%

    No Known Activations