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

    Neuronpedia

    INDEX
    Explanations

    magic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    圳
    -0.08
    eres
    -0.07
    .latitude
    -0.07
    、高
    -0.07
     schvál
    -0.07
     Built
    -0.07
    eph
    -0.06
    Benefits
    -0.06
    บาย
    -0.06
     watchers
    -0.06
    POSITIVE LOGITS
     تس
    0.06
    At
    0.06
    Để
    0.06
    งม
    0.06
    	want
    0.06
     departed
    0.06
    ToUpdate
    0.06
    allocator
    0.06
     iCloud
    0.05
    _Register
    0.05
    Act Density 0.008%

    No Known Activations