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

    Neuronpedia

    INDEX
    Explanations

    Function words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     вій
    -0.07
    _HI
    -0.07
    کنان
    -0.06
    _RM
    -0.06
     rm
    -0.06
     bottled
    -0.06
    ｜
    -0.06
    ่าน
    -0.06
     integrity
    -0.06
     答
    -0.06
    POSITIVE LOGITS
     animator
    0.06
    (coll
    0.06
    ows
    0.06
    (require
    0.06
    .workspace
    0.06
     Erot
    0.06
    -items
    0.06
    UILDER
    0.06
     ObjectType
    0.06
    overs
    0.06
    Act Density 0.038%

    No Known Activations