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

    Neuronpedia

    INDEX
    Explanations

    Pal

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tear
    -0.08
    6
    -0.08
    角落
    -0.07
    新征程
    -0.07
     soy
    -0.07
    3
    -0.07
     flooded
    -0.07
     crash
    -0.07
     проект
    -0.07
    纷
    -0.07
    POSITIVE LOGITS
     Pal
    0.07
     kỳ
    0.07
    방송
    0.07
    ᄃ
    0.07
    פיצוי
    0.07
     <|
    0.07
    维奇
    0.07
    料
    0.07
    �
    0.06
    P
    0.06
    Act Density 0.024%

    No Known Activations