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

    Neuronpedia

    INDEX
    Explanations

    sense

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    checking
    -0.06
    quiet
    -0.06
     الدر
    -0.06
    _trace
    -0.06
    ा�
    -0.06
     propor
    -0.06
    avour
    -0.06
    likle
    -0.06
    ğim
    -0.06
     المؤ
    -0.06
    POSITIVE LOGITS
     sense
    0.09
    sense
    0.09
    づ
    0.07
     Sense
    0.07
    /'.$
    0.07
    奈
    0.06
     mortgages
    0.06
    ">*</
    0.06
     sensible
    0.06
     無
    0.06
    Act Density 0.008%

    No Known Activations