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

    Neuronpedia

    INDEX
    Explanations

    government positions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    CEED
    -0.07
    -driving
    -0.06
    restrial
    -0.06
     tonnes
    -0.06
     voters
    -0.06
     McL
    -0.06
     correlations
    -0.06
    μές
    -0.06
     ارزش
    -0.06
     forgive
    -0.06
    POSITIVE LOGITS
    cstdint
    0.07
     predecess
    0.07
    министра
    0.07
     Position
    0.07
    arg
    0.06
    abc
    0.06
     hải
    0.06
     midterm
    0.06
    ías
    0.06
    .expand
    0.06
    Act Density 0.316%

    No Known Activations