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

    Neuronpedia

    INDEX
    Explanations

    run

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mitarbeitern
    -0.09
     substrates
    -0.08
    zah
    -0.08
     faaliyet
    -0.08
     mpl
    -0.08
     berlaku
    -0.08
    ‍ഡ്
    -0.08
    rijke
    -0.08
     reger
    -0.08
     platen
    -0.08
    POSITIVE LOGITS
     perfection
    0.10
     perfected
    0.08
     perfecto
    0.08
     religious
    0.08
    Screenshot
    0.08
     religieux
    0.08
     Screenshot
    0.08
    length
    0.08
    Recorder
    0.08
    fur
    0.08
    Act Density 0.004%

    No Known Activations