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

    Neuronpedia

    INDEX
    Explanations

    most famous

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     characterised
    0.43
     आकर्षक
    0.42
     Description
    0.41
     appreciated
    0.40
     descripción
    0.39
     generally
    0.38
     descripcion
    0.38
     respected
    0.38
     perceived
    0.38
     customarily
    0.38
    POSITIVE LOGITS
     famous
    1.63
    famous
    1.59
    Famous
    1.49
     famoso
    1.40
     Famous
    1.35
     famosos
    1.35
     famosa
    1.33
     বিখ্যাত
    1.30
     fam
    1.24
     berühm
    1.24
    Act Density 0.034%

    No Known Activations