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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ölç
    -0.07
     Hector
    -0.06
    _perms
    -0.06
     oath
    -0.06
    bitset
    -0.06
     Vector
    -0.06
     ổ
    -0.06
    aims
    -0.06
    _xlabel
    -0.06
    íně
    -0.06
    POSITIVE LOGITS
    دو
    0.06
     машин
    0.06
     cultura
    0.06
    ButtonItem
    0.06
    вей
    0.06
     والأ
    0.06
     "%
    0.06
     Braves
    0.06
    /a
    0.06
    (update
    0.06
    Act Density 0.002%

    No Known Activations