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

    Neuronpedia

    INDEX
    Explanations

    as a / an / well

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    0.19
    ’
    0.18
    }=\
    0.18
     Cuando
    0.17
     ระ
    0.17
     Remains
    0.16
    }(\
    0.16
     menet
    0.16
    When
    0.16
    หรือ
    0.16
    POSITIVE LOGITS
     opposed
    0.38
    sembles
    0.31
    ymmet
    0.29
     it
    0.28
     well
    0.27
     будто
    0.27
    cribing
    0.27
     evidenced
    0.27
     far
    0.25
     oppose
    0.25
    Act Density 0.089%

    No Known Activations