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

    Neuronpedia

    INDEX
    Explanations

    numbers and fractions

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    指针
    0.74
    经
    0.71
     ישראל
    0.67
    έλ
    0.67
     privadas
    0.66
    吧
    0.66
     Málaga
    0.65
     metac
    0.64
     nacional
    0.64
     trasera
    0.64
    POSITIVE LOGITS
     replaces
    0.69
     Ca
    0.65
    Ca
    0.65
     Seventh
    0.62
     Reproduced
    0.62
    irty
    0.62
     Exchanges
    0.62
     EACH
    0.60
    യ്ക്ക്
    0.60
     бір
    0.60
    Act Density 0.000%

    No Known Activations