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

    Neuronpedia

    INDEX
    Explanations

    's

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    inate
    -0.07
     chores
    -0.07
    ergency
    -0.06
    Correct
    -0.06
     meals
    -0.06
     wakes
    -0.06
    육
    -0.06
    Signed
    -0.06
    ерв
    -0.06
     مدل
    -0.06
    POSITIVE LOGITS
     Hess
    0.07
    hum
    0.06
    opathy
    0.06
     Stephens
    0.06
    .story
    0.06
    FINAL
    0.06
    .setLevel
    0.06
     vlády
    0.06
    感觉
    0.06
     tattoo
    0.06
    Act Density 0.000%

    No Known Activations