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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gamers
    -0.06
    ////////////////////////////////////////////////////////////////////////////////
    -0.06
     pregnancies
    -0.06
     bricks
    -0.06
    WORD
    -0.06
    ीब
    -0.06
    wie
    -0.06
     deserving
    -0.06
    �
    -0.06
    Abr
    -0.06
    POSITIVE LOGITS
     osp
    0.06
    .Null
    0.06
     flower
    0.06
     Todd
    0.06
    .pending
    0.06
     Rays
    0.06
     domaine
    0.06
     implemented
    0.06
    ',
↵
    0.06
     тай
    0.06
    Act Density 0.186%

    No Known Activations