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

    Neuronpedia

    INDEX
    Explanations

    256

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     axe
    0.54
     SND
    0.46
     Six
    0.46
    六
    0.44
     ax
    0.41
     Axe
    0.40
     six
    0.40
     ছয়
    0.39
    勇
    0.39
     أش
    0.38
    POSITIVE LOGITS
    可能な
    0.40
     തന്നെ
    0.39
    ^{
    0.38
    ^(
    0.37
    elecimento
    0.37
    Propagation
    0.37
     Geschichte
    0.36
     রাজধান
    0.36
    நி
    0.36
    이를
    0.36
    Act Density 0.012%

    No Known Activations