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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .yahoo
    -0.06
     mainly
    -0.06
     zeros
    -0.06
    (pattern
    -0.06
     toolStrip
    -0.06
     جامع
    -0.06
    내
    -0.06
    htdocs
    -0.06
    响
    -0.06
     sew
    -0.06
    POSITIVE LOGITS
     wee
    0.07
     Pend
    0.07
     Hello
    0.07
     plain
    0.06
    thalm
    0.06
     okum
    0.06
    dee
    0.06
     panc
    0.06
     ….
    0.06
    ı
    0.06
    Act Density 0.128%

    No Known Activations