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

    Neuronpedia

    INDEX
    Explanations

    mixed number conversion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     differing
    0.44
     varying
    0.43
     convert
    0.43
     mutate
    0.41
     blurring
    0.40
     different
    0.39
     multiplying
    0.39
     spraying
    0.39
     bowling
    0.38
     Ninety
    0.38
    POSITIVE LOGITS
    )):
    0.42
     или
    0.40
     ಅಥವಾ
    0.40
     houdt
    0.40
    वेश
    0.39
    Appointment
    0.39
    或是
    0.38
     उन्नति
    0.38
    )]:
    0.38
     možete
    0.38
    Act Density 0.000%

    No Known Activations