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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /Library
    -0.07
     ماسه
    -0.07
    })"↵
    -0.06
    Tester
    -0.06
    Study
    -0.06
    砂
    -0.06
    .bam
    -0.06
    芝
    -0.06
     katkı
    -0.06
     cleanly
    -0.06
    POSITIVE LOGITS
     sympath
    0.06
    oucí
    0.06
     immac
    0.06
     Qui
    0.06
    ağa
    0.06
    �다
    0.06
    REFERRED
    0.06
     spreadsheet
    0.06
     reigning
    0.06
     assertTrue
    0.06
    Act Density 0.076%

    No Known Activations