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

    Neuronpedia

    INDEX
    Explanations

    multiple languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (pow
    -0.07
     tenía
    -0.07
    "]];↵
    -0.06
     swo
    -0.06
     balancing
    -0.06
     па
    -0.06
    (help
    -0.06
    (GTK
    -0.06
     nye
    -0.06
    (TAG
    -0.06
    POSITIVE LOGITS
    hy
    0.06
     Crusher
    0.06
    /backend
    0.06
     adjustments
    0.06
     sandy
    0.06
    ener
    0.06
    spar
    0.06
    cher
    0.06
    рд
    0.06
    igue
    0.06
    Act Density 0.024%

    No Known Activations