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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ctr
    -0.07
     Junk
    -0.06
    Stuff
    -0.06
     cramped
    -0.06
    cg
    -0.06
    disc
    -0.06
     func
    -0.06
     pentru
    -0.06
     organs
    -0.06
     Từ
    -0.06
    POSITIVE LOGITS
    .cell
    0.07
    “We
    0.07
    orsch
    0.07
    哪
    0.06
    股票
    0.06
    Xi
    0.06
     اساسی
    0.06
     Afrika
    0.06
    (background
    0.06
    ascript
    0.06
    Act Density 0.157%

    No Known Activations