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

    Neuronpedia

    INDEX
    Explanations

    graph layout and testing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BJ
    0.75
     więc
    0.72
    सूर्य
    0.72
     mattina
    0.69
    рати
    0.69
    śmy
    0.68
     صبح
    0.68
    เหล่านี้
    0.68
    하면
    0.67
     menjel
    0.67
    POSITIVE LOGITS
    e
    0.86
    Ls
    0.75
    a
    0.75
     hashlib
    0.75
    o
    0.75
     that
    0.75
    ка
    0.72
     operand
    0.72
    eol
    0.71
    eaa
    0.71
    Act Density 0.068%

    No Known Activations