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

    Neuronpedia

    INDEX
    Explanations

    5

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    istributor
    -0.07
     biod
    -0.07
     korum
    -0.07
     Bod
    -0.07
    он
    -0.06
     illust
    -0.06
     ZX
    -0.06
     universally
    -0.06
     experiment
    -0.06
    stor
    -0.06
    POSITIVE LOGITS
    opened
    0.08
    _Bool
    0.07
    ặ
    0.06
    Perl
    0.06
    리는
    0.06
    ;top
    0.06
     взя
    0.06
    ैं.
    0.06
     dumps
    0.06
    ๆ
    0.06
    Act Density 0.004%

    No Known Activations