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

    Neuronpedia

    INDEX
    Explanations

    relations between data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    _{
    0.21
    0.21
     depiction
    0.20
    _
    0.20
     were
    0.20
    )،
    0.20
    ):
    0.19
    *.
    0.19
    .,
    0.19
    *,
    0.19
    POSITIVE LOGITS
     для
    0.31
     from
    0.30
    จาก
    0.30
     через
    0.29
     through
    0.28
     without
    0.28
     फ्रॉम
    0.28
     với
    0.28
     WITHOUT
    0.27
     уйнагыз
    0.27
    Act Density 3.826%

    No Known Activations