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
    _partner
    -0.07
    شركة
    -0.06
    alles
    -0.06
    "You
    -0.06
    เค
    -0.06
    “You
    -0.06
    itore
    -0.06
    .Prop
    -0.06
    ̀
    -0.06
    sole
    -0.06
    POSITIVE LOGITS
     Slot
    0.06
     вк
    0.06
    ようです
    0.06
     bieten
    0.06
     DIM
    0.06
     absl
    0.06
    ază
    0.06
     cyst
    0.06
     rut
    0.06
     초기
    0.06
    Act Density 0.002%

    No Known Activations