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

    Neuronpedia

    INDEX
    Explanations

    personality

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     brief
    -0.08
    隘
    -0.08
     إنه
    -0.08
    战机
    -0.07
    ‡
    -0.07
    WIDTH
    -0.07
    ده
    -0.07
    毡
    -0.07
    西部
    -0.07
    深切
    -0.07
    POSITIVE LOGITS
     Khal
    0.07
     ejemplo
    0.06
    읻
    0.06
     popup
    0.06
    asyarak
    0.06
    Taylor
    0.06
     популяр
    0.06
     and
    0.06
     Shake
    0.06
     Damon
    0.06
    Act Density 0.011%

    No Known Activations