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

    Neuronpedia

    INDEX
    Explanations

    bounding boxes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    шли
    -0.07
    idental
    -0.07
     справа
    -0.06
    _Char
    -0.06
    际
    -0.06
     Ree
    -0.06
    double
    -0.06
    _mu
    -0.06
     Asi
    -0.06
    lero
    -0.06
    POSITIVE LOGITS
     ‪
    0.07
    먹
    0.07
     fron
    0.06
    (distance
    0.06
    caster
    0.06
     дум
    0.06
     ries
    0.06
    product
    0.06
     <?=
    0.06
     достиг
    0.06
    Act Density 0.010%

    No Known Activations