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

    Neuronpedia

    INDEX
    Explanations

    equals sign

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Princeton
    -0.08
     renewal
    -0.08
     overridden
    -0.08
     reunion
    -0.08
    .nil
    -0.08
     interfer
    -0.07
     interfering
    -0.07
     fulfills
    -0.07
     summ
    -0.07
    Learn
    -0.07
    POSITIVE LOGITS
     halve
    0.09
     Parcel
    0.08
    ியாக
    0.08
     Route
    0.08
    -route
    0.08
    aryana
    0.07
     trous
    0.07
     halves
    0.07
     sospe
    0.07
     respekt
    0.07
    Act Density 0.016%

    No Known Activations