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

    Neuronpedia

    INDEX
    Explanations

    circuit layout

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Jin
    -0.07
     dicho
    -0.07
     Они
    -0.06
     Giovanni
    -0.06
    -follow
    -0.06
     Compatibility
    -0.06
    ("&
    -0.06
     Catal
    -0.06
    qed
    -0.06
    -New
    -0.06
    POSITIVE LOGITS
     mount
    0.07
    ząd
    0.07
     socket
    0.06
    ıda
    0.06
     sourceMappingURL
    0.06
    ANGE
    0.06
     Screens
    0.06
    いの
    0.06
    PAL
    0.06
     travelers
    0.06
    Act Density 0.018%

    No Known Activations