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

    Neuronpedia

    INDEX
    Explanations

    const

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     בשנים
    -0.07
    ﭓ
    -0.07
     Circle
    -0.07
     Irr
    -0.07
    舅舅
    -0.06
    ဖ
    -0.06
    ARB
    -0.06
    绘画
    -0.06
    пе
    -0.06
     noktas
    -0.06
    POSITIVE LOGITS
     querying
    0.07
     hại
    0.07
    穩
    0.07
     book
    0.07
    可靠
    0.07
    僵尸
    0.07
    xxxxxxxx
    0.07
    糖尿病
    0.06
     chu
    0.06
    缩减
    0.06
    Act Density 0.004%

    No Known Activations