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

    Neuronpedia

    INDEX
    Explanations

    Quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     буд
    -0.07
     ذات
    -0.07
    \Facades
    -0.06
    เสน
    -0.06
    �
    -0.06
     remarks
    -0.06
    ');?></
    -0.06
     grandma
    -0.06
     навіть
    -0.06
     Premier
    -0.06
    POSITIVE LOGITS
    turn
    0.07
    [res
    0.07
     Purple
    0.07
    Α
    0.06
    cord
    0.06
    .writeFile
    0.06
    usk
    0.06
    oop
    0.06
    ↵↵
    0.06
    logs
    0.06
    Act Density 0.016%

    No Known Activations