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

    Neuronpedia

    INDEX
    Explanations

    positions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (this
    -0.08
    WOOD
    -0.07
     alım
    -0.06
    Slots
    -0.06
    565
    -0.06
    wood
    -0.06
    ォ
    -0.06
    hape
    -0.06
     Swing
    -0.06
    -dropdown
    -0.06
    POSITIVE LOGITS
     FileStream
    0.07
     فيلم
    0.07
     FVector
    0.06
     deser
    0.06
     Stock
    0.06
    -parse
    0.06
    江
    0.06
    Winter
    0.06
     身
    0.06
     lille
    0.06
    Act Density 0.000%

    No Known Activations