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

    Neuronpedia

    INDEX
    Explanations

    steel

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    xico
    -0.07
    unordered
    -0.07
     Gee
    -0.06
    .description
    -0.06
     Saras
    -0.06
    یکی
    -0.06
     officially
    -0.06
    <link
    -0.06
    ôte
    -0.06
     Nicholson
    -0.06
    POSITIVE LOGITS
     improvis
    0.08
    |}↵
    0.07
     anlayış
    0.06
     بات
    0.06
     tradition
    0.06
     Engineer
    0.06
    /Common
    0.06
     */;↵
    0.06
     німець
    0.06
     Mul
    0.06
    Act Density 0.075%

    No Known Activations