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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     initialized
    -0.07
    .Owner
    -0.07
     whip
    -0.07
     Members
    -0.07
     converge
    -0.06
    Calcul
    -0.06
     Dak
    -0.06
     hobby
    -0.06
    Control
    -0.06
     Likes
    -0.06
    POSITIVE LOGITS
     самой
    0.07
    cies
    0.07
    okrat
    0.07
     звичай
    0.07
     souvis
    0.06
    ção
    0.06
    oland
    0.06
     headset
    0.06
    进
    0.06
     anmeld
    0.06
    Act Density 0.018%

    No Known Activations