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

    Neuronpedia

    INDEX
    Explanations

    source code comments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _calc
    -0.07
    גובה
    -0.06
     clicking
    -0.06
    script
    -0.06
     premium
    -0.06
     quantities
    -0.06
     كافة
    -0.06
    溅
    -0.06
    훍
    -0.06
     sider
    -0.06
    POSITIVE LOGITS
    任期
    0.08
    硙
    0.08
     LSB
    0.07
    铡
    0.07
     абсолют
    0.07
     karde
    0.07
    娀
    0.07
    펴
    0.07
    NAL
    0.07
    鲞
    0.07
    Act Density 0.019%

    No Known Activations