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

    Neuronpedia

    INDEX
    Explanations

    howdy greeting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sak
    0.45
     freest
    0.43
     portland
    0.42
     REST
    0.42
     abstracto
    0.40
     Sak
    0.39
     Astronomy
    0.39
    modes
    0.39
     sekt
    0.39
     static
    0.38
    POSITIVE LOGITS
    ্ি
    0.48
     incipient
    0.43
    initely
    0.42
    =?,
    0.42
    ы
    0.42
    蚪
    0.41
    嵐
    0.40
    elerinin
    0.40
    IdleSync
    0.39
     кнопку
    0.39
    Act Density 0.000%

    No Known Activations