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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    yst
    -0.07
    чила
    -0.07
    opened
    -0.06
     Karnataka
    -0.06
     bw
    -0.06
     gw
    -0.06
    -0.06
     salts
    -0.06
     horrors
    -0.06
    一样
    -0.06
    POSITIVE LOGITS
     prestige
    0.07
     ster
    0.07
    .sendFile
    0.06
    ilor
    0.06
     ویکی
    0.06
     continuation
    0.06
     referencedColumnName
    0.06
    ellungen
    0.06
    edium
    0.06
     scalability
    0.06
    Act Density 0.000%

    No Known Activations