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

    Neuronpedia

    INDEX
    Explanations

    Technical language/symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     전화
    -0.06
    르는
    -0.06
    how
    -0.06
     والتي
    -0.06
     Perf
    -0.06
     cầm
    -0.06
    blend
    -0.06
     اقتص
    -0.06
    correct
    -0.06
     Extract
    -0.06
    POSITIVE LOGITS
     Giants
    0.07
    анні
    0.06
    .Depth
    0.06
     membrane
    0.06
     Bunny
    0.06
     provoc
    0.06
     Jako
    0.06
     Tent
    0.06
     SetUp
    0.06
     Via
    0.06
    Act Density 0.000%

    No Known Activations