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

    Neuronpedia

    INDEX
    Explanations

    the following

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     the
    0.57
     those
    0.55
     lim
    0.53
     foolproof
    0.49
     beyond
    0.49
    ,
    0.48
     belie
    0.46
     lump
    0.46
     wholeheartedly
    0.46
     thoſe
    0.46
    POSITIVE LOGITS
    I
    0.54
    для
    0.52
    などの
    0.51
     জন্য
    0.49
    なので
    0.46
    など
    0.44
    <0x91>
    0.44
     diciamo
    0.43
     அமைப்பு
    0.43
     ambayo
    0.43
    Act Density 0.191%

    No Known Activations