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

    Neuronpedia

    INDEX
    Explanations

    config

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Listing
    -0.08
    zell
    -0.07
     playful
    -0.07
     Transfer
    -0.06
    .Text
    -0.06
    .Power
    -0.06
     frame
    -0.06
    exchange
    -0.06
     тол
    -0.06
    Array
    -0.06
    POSITIVE LOGITS
    ANCED
    0.06
     меня
    0.06
    ))[
    0.06
    disp
    0.06
    按照
    0.06
     unterschied
    0.06
     DNC
    0.06
     determinant
    0.06
     nun
    0.06
    ンダ
    0.06
    Act Density 0.016%

    No Known Activations