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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     JW
    -0.07
    /ar
    -0.07
     وذلك
    -0.06
    екотор
    -0.06
     nuru
    -0.06
    ンピ
    -0.06
    Telefono
    -0.06
     propri
    -0.06
     dever
    -0.06
     واست
    -0.06
    POSITIVE LOGITS
    =
    0.11
    =m
    0.07
    )=
    0.07
    =A
    0.07
    =M
    0.07
     deductions
    0.07
    +
    0.07
    لاة
    0.06
    岩
    0.06
     fiscal
    0.06
    Act Density 0.005%

    No Known Activations