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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _pairs
    -0.07
    -metal
    -0.06
    ('${
    -0.06
     tend
    -0.06
     başlay
    -0.06
    Rectangle
    -0.06
     bonding
    -0.06
    ogram
    -0.06
     scam
    -0.06
    ion
    -0.06
    POSITIVE LOGITS
     onNext
    0.06
    ardless
    0.06
     Netflix
    0.06
     Annex
    0.06
     effortless
    0.06
     βασ
    0.06
    Witness
    0.06
    Think
    0.06
     ########.
    0.06
     lecken
    0.06
    Act Density 0.005%

    No Known Activations