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

    Neuronpedia

    INDEX
    Explanations

    Measure theory

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    िब
    -0.07
    Demo
    -0.07
     stirring
    -0.07
    eland
    -0.07
    樹
    -0.07
    まる
    -0.06
    temps
    -0.06
     sendo
    -0.06
     steer
    -0.06
    Rich
    -0.06
    POSITIVE LOGITS
     регули
    0.06
     Комп
    0.06
    SYSTEM
    0.06
    apeut
    0.06
    _DIG
    0.06
     jealousy
    0.06
    .ascii
    0.06
     رشته
    0.06
    لیت
    0.06
     COMMENTS
    0.06
    Act Density 0.012%

    No Known Activations