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

    Neuronpedia

    INDEX
    Explanations

    completing work

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Relationships
    -0.09
    relationships
    -0.08
     betekenis
    -0.08
     dhi
    -0.08
     relaties
    -0.08
     relationships
    -0.08
     tease
    -0.08
     yerləş
    -0.08
     مجموعه
    -0.07
     inzicht
    -0.07
    POSITIVE LOGITS
     supplemented
    0.09
     intermitt
    0.09
    Started
    0.09
     enlisted
    0.09
     collaborated
    0.09
     switches
    0.09
     assisted
    0.08
     wast
    0.08
     المقا
    0.08
    _STARTED
    0.08
    Act Density 0.016%

    No Known Activations