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

    Neuronpedia

    INDEX
    Explanations

    rhodes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ierarchy
    -0.07
     버
    -0.07
    โก
    -0.07
    汽车
    -0.07
    신청
    -0.06
    _Vert
    -0.06
    �
    -0.06
     tính
    -0.06
    �
    -0.06
     Converter
    -0.06
    POSITIVE LOGITS
     Rhodes
    0.17
    าผ
    0.08
    HX
    0.08
     виды
    0.07
     重
    0.07
     blends
    0.07
    POSE
    0.07
     lodge
    0.07
    illed
    0.07
     Bras
    0.07
    Act Density 0.000%

    No Known Activations