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

    Neuronpedia

    INDEX
    Explanations

    research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    𝘷
    -0.07
    的回答
    -0.07
    &A
    -0.07
    改革委
    -0.07
    brtc
    -0.07
     Satellite
    -0.07
     SYSTEM
    -0.07
    DMETHOD
    -0.06
     executing
    -0.06
    _EXTENSION
    -0.06
    POSITIVE LOGITS
    莰
    0.08
    푼
    0.07
     ما
    0.06
    평
    0.06
    omain
    0.06
     Bengals
    0.06
    全局
    0.06
     Trent
    0.06
    ansas
    0.06
     wegen
    0.06
    Act Density 0.775%

    No Known Activations