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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rise
    -0.07
    (simp
    -0.06
     عبر
    -0.06
     fuss
    -0.06
    .answer
    -0.06
    /Footer
    -0.06
    brush
    -0.06
    (step
    -0.06
     semble
    -0.06
    -Pack
    -0.06
    POSITIVE LOGITS
     Stuttgart
    0.07
     hạng
    0.07
    شاه
    0.07
    illes
    0.07
     застосування
    0.06
     rocket
    0.06
     circular
    0.06
     premature
    0.06
     ","
    0.06
    >((
    0.06
    Act Density 0.032%

    No Known Activations