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

    Neuronpedia

    INDEX
    Explanations

    source

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ünkü
    -0.07
     chút
    -0.07
    -folder
    -0.06
    208
    -0.06
     Мор
    -0.06
    ==="
    -0.06
    718
    -0.06
    lsruhe
    -0.06
     Device
    -0.06
     isEqual
    -0.06
    POSITIVE LOGITS
     страш
    0.06
    ARR
    0.06
    าธ
    0.06
     imgs
    0.06
     Hond
    0.06
    endra
    0.06
     persuaded
    0.06
    ika
    0.06
     풀
    0.06
    |r
    0.06
    Act Density 0.001%

    No Known Activations