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

    Neuronpedia

    INDEX
    Explanations

    here's why,

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     the
    1.22
    the
    1.06
    ationen
    1.06
    uck
    1.02
    aka
    1.02
     करणे
    1.02
     agréable
    1.02
    ora
    0.98
    Boundary
    0.98
     Aucun
    0.98
    POSITIVE LOGITS
     이유는
    1.14
     जिस
    1.03
     जिन
    1.02
     hề
    0.96
    忤
    0.96
    rrbracket
    0.95
     simmer
    0.95
    倘
    0.94
    től
    0.93
    ed
    0.93
    Act Density 0.238%

    No Known Activations