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

    Neuronpedia

    INDEX
    Explanations

    know that / understand that / remember that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ہو۔
    0.57
     گئی۔
    0.48
     ہوں۔
    0.47
     Он
    0.47
    Ма
    0.46
     جائے۔
    0.46
     വേദിക
    0.45
     کریں۔
    0.44
     കൂട
    0.44
     گی۔
    0.43
    POSITIVE LOGITS
    ,
    0.76
     while
    0.73
    ,"
    0.68
    ,]
    0.65
    ,”
    0.65
     since
    0.64
     though
    0.64
    ,’
    0.64
     unequivocally
    0.64
     nobody
    0.63
    Act Density 0.124%

    No Known Activations