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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ru
    -0.06
     ce
    -0.06
    eea
    -0.06
     приобрет
    -0.06
     plat
    -0.06
    нання
    -0.06
     правда
    -0.06
     Ru
    -0.06
    ке
    -0.06
     Going
    -0.06
    POSITIVE LOGITS
    _MAKE
    0.07
    .Show
    0.07
     admirable
    0.06
    _;↵
    0.06
     referring
    0.06
    Iterator
    0.06
    SuppressLint
    0.06
     paycheck
    0.06
    „ظ
    0.06
    ():
↵
    0.06
    Act Density 0.142%

    No Known Activations