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

    Neuronpedia

    INDEX
    Explanations

    -U

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     everything
    -0.07
     preset
    -0.07
    דק
    -0.07
    Insert
    -0.07
    /setup
    -0.07
    _MODE
    -0.07
     elements
    -0.07
    split
    -0.06
     Sergio
    -0.06
    SC
    -0.06
    POSITIVE LOGITS
     pursued
    0.07
     Lam
    0.07
     Shrine
    0.06
    Bear
    0.06
     Batter
    0.06
    Beam
    0.06
    APON
    0.06
     PodsDummy
    0.06
    损
    0.06
    Later
    0.06
    Act Density 0.001%

    No Known Activations