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

    Neuronpedia

    INDEX
    Explanations

    Reading and writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     تف
    -0.06
    .program
    -0.06
    Evaluator
    -0.06
    inox
    -0.06
     NPR
    -0.06
     نحو
    -0.06
     équip
    -0.06
    یستم
    -0.06
     العظ
    -0.06
     -------------
    -0.06
    POSITIVE LOGITS
     chooses
    0.07
     errorMessage
    0.07
     nie
    0.07
    		
↵
    0.06
     coded
    0.06
     Wedding
    0.06
    ellt
    0.06
     Kostenlos
    0.06
     имму
    0.06
     Hy
    0.06
    Act Density 0.193%

    No Known Activations