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

    Neuronpedia

    INDEX
    Explanations

    Dates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ﭻ
    -0.08
    🎒
    -0.07
     бил
    -0.07
    ㎛
    -0.07
    �
    -0.07
    🗾
    -0.07
    יכה
    -0.07
    คะ
    -0.07
    bett
    -0.07
    ENSOR
    -0.07
    POSITIVE LOGITS
    巷
    0.07
    恶劣
    0.07
    ог
    0.07
    ﹻ
    0.07
    .length
    0.07
    溅
    0.06
    辛
    0.06
    [port
    0.06
     respectively
    0.06
     Hok
    0.06
    Act Density 0.002%

    No Known Activations