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

    Neuronpedia

    INDEX
    Explanations

    retry

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dedicated
    -0.07
     collide
    -0.07
    沈阳
    -0.07
     ______
    -0.07
    冲动
    -0.06
    廛
    -0.06
    ////////////////////////////////
    -0.06
    ,Object
    -0.06
    phones
    -0.06
    _list
    -0.06
    POSITIVE LOGITS
     THINK
    0.07
     er
    0.07
    wed
    0.07
    .Nombre
    0.07
    增持
    0.07
     Har
    0.07
    lyn
    0.06
     asylum
    0.06
    .table
    0.06
     liking
    0.06
    Act Density 0.099%

    No Known Activations