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

    Neuronpedia

    INDEX
    Explanations

    me

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    বিশেষ
    0.71
     egész
    0.66
    ก็จะ
    0.65
    櫥
    0.65
    幾乎
    0.64
    地に
    0.63
    തിനു
    0.63
     budú
    0.63
     ziemlich
    0.62
    ிகளும்
    0.62
    POSITIVE LOGITS
     how
    1.69
     How
    1.35
    how
    1.35
     why
    1.31
    How
    1.26
     HOW
    1.22
     cómo
    1.20
     bagaimana
    1.17
     as
    1.17
     what
    1.16
    Act Density 0.020%

    No Known Activations