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

    Neuronpedia

    INDEX
    Explanations

    all

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Unexpected
    -0.06
     GenerationType
    -0.06
     Jury
    -0.06
     Salman
    -0.06
    (月
    -0.06
     setPage
    -0.06
     guarantee
    -0.06
     Kenneth
    -0.06
     Unexpected
    -0.06
     versatility
    -0.06
    POSITIVE LOGITS
     all
    0.09
     ALL
    0.07
    “All
    0.07
    ...',
    0.07
    组织
    0.06
    .word
    0.06
    iter
    0.06
    otive
    0.06
     گذاری
    0.06
     autour
    0.06
    Act Density 0.061%

    No Known Activations