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
     cases
    -0.07
    新增
    -0.07
     Theme
    -0.07
     mastered
    -0.07
     تشخیص
    -0.06
     Tomas
    -0.06
     Zusammen
    -0.06
    agnosis
    -0.06
     selber
    -0.06
     Casey
    -0.06
    POSITIVE LOGITS
     friendly
    0.06
    ’nın
    0.06
     sit
    0.06
    ESPN
    0.06
    坐在
    0.06
     estr
    0.06
     marketers
    0.06
     三
    0.06
    ände
    0.06
     sin
    0.06
    Act Density 0.010%

    No Known Activations