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

    Neuronpedia

    INDEX
    Explanations

    Emphatic qualifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    k
    0.56
     ,
    0.48
     (
    0.45
     or
    0.45
    z
    0.44
    ID
    0.43
     bzw
    0.42
    Maybe
    0.41
    maybe
    0.41
     якобы
    0.41
    POSITIVE LOGITS
    પણે
    0.49
    पणे
    0.47
    ныгы
    0.47
    هداف
    0.47
    olutamente
    0.46
    ísim
    0.45
    politik
    0.45
    ര്യ
    0.44
    भव
    0.43
     justiciable
    0.43
    Act Density 0.208%

    No Known Activations