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

    Neuronpedia

    INDEX
    Explanations

    instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     übrigens
    -0.08
    INO
    -0.07
     Battles
    -0.07
     pourtant
    -0.07
     Allerg
    -0.07
    STER
    -0.07
     Earrings
    -0.07
    aille
    -0.07
     mencoba
    -0.07
     Coupons
    -0.07
    POSITIVE LOGITS
     möglichst
    0.11
     ולה
    0.10
    ，提高
    0.10
     understand
    0.09
    能够
    0.09
     максимально
    0.08
    ，实现
    0.08
     zodat
    0.08
    了解
    0.08
     thereby
    0.08
    Act Density 0.175%

    No Known Activations