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

    Neuronpedia

    INDEX
    Explanations

    following punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    उसके
    0.52
     niego
    0.50
    उनके
    0.50
     його
    0.48
     onun
    0.48
    there
    0.47
     ним
    0.47
     différentes
    0.44
    ités
    0.43
     suas
    0.43
    POSITIVE LOGITS
     لدى
    0.52
     kuid
    0.45
     these
    0.41
    会让
    0.40
    界
    0.40
     любят
    0.39
     этих
    0.38
     אך
    0.37
     পারেননি
    0.37
    mayan
    0.37
    Act Density 0.054%

    No Known Activations