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

    Neuronpedia

    INDEX
    Explanations

    after "is"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :
    0.54
    ?
    0.51
    ...
    0.43
    .
    0.40
     тобто
    0.38
    ":
    0.37
     -
    0.37
    ОО
    0.37
    !
    0.37
    ؟
    0.37
    POSITIVE LOGITS
     étant
    0.53
     đc
    0.51
    étant
    0.50
    remain
    0.48
     være
    0.47
    should
    0.46
     തന്നെയാണ്
    0.45
     jugó
    0.45
    一直是
    0.44
    已经被
    0.44
    Act Density 0.005%

    No Known Activations