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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    τεύ
    -0.06
    踏
    -0.06
    囲
    -0.06
     hora
    -0.06
    言って
    -0.06
    وقف
    -0.06
    那样
    -0.06
     warmth
    -0.06
    .$
    -0.06
    (Sub
    -0.06
    POSITIVE LOGITS
    _DEF
    0.07
    HAL
    0.07
     progression
    0.07
     vot
    0.07
    اس
    0.06
    แชม
    0.06
     ay
    0.06
     dotenv
    0.06
    /response
    0.06
     CLR
    0.06
    Act Density 0.007%

    No Known Activations