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

    Neuronpedia

    INDEX
    Explanations

    elegant

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .disk
    -0.07
    -0.07
    ремя
    -0.07
    ohn
    -0.07
    "People
    -0.06
    oud
    -0.06
    getField
    -0.06
    rx
    -0.06
    ates
    -0.06
     deviations
    -0.06
    POSITIVE LOGITS
     перев
    0.08
     découvrir
    0.07
     BAT
    0.07
    迫
    0.06
    BAT
    0.06
     intimid
    0.06
    esion
    0.06
    εξ
    0.06
    walker
    0.06
     spl
    0.06
    Act Density 0.027%

    No Known Activations