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

    Neuronpedia

    INDEX
    Explanations

    model turn start

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     couldnt
    0.97
     करिकुलम
    0.93
     売場面積
    0.91
     predsjed
    0.91
     reconoc
    0.90
     ncols
    0.88
    rrbracket
    0.88
     कहें
    0.88
     hadc
    0.87
     partialX
    0.87
    POSITIVE LOGITS
    לה
    0.59
     happiest
    0.54
     a
    0.53
     :
    0.52
    पान
    0.52
     Af
    0.52
    Mot
    0.52
    onomic
    0.51
     Az
    0.51
    Af
    0.51
    Act Density 0.138%

    No Known Activations