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
     BY
    -0.06
     notorious
    -0.06
    ，看
    -0.06
     UB
    -0.06
     день
    -0.06
     Of
    -0.06
    ะแนน
    -0.05
    on
    -0.05
     Alv
    -0.05
     cou
    -0.05
    POSITIVE LOGITS
    となった
    0.07
     bás
    0.07
    _TOGGLE
    0.07
    Bird
    0.07
     chế
    0.06
     台
    0.06
     cube
    0.06
     ==(
    0.06
     {?}
    0.06
     única
    0.06
    Act Density 0.000%

    No Known Activations