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

    Neuronpedia

    INDEX
    Explanations

    code snippets, formal writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     shard
    -0.06
     běž
    -0.06
     messageId
    -0.06
    τρέ
    -0.06
    >--
    -0.06
     Briggs
    -0.06
     resh
    -0.06
     treaty
    -0.06
     knocking
    -0.06
    $stmt
    -0.06
    POSITIVE LOGITS
    .getLog
    0.07
    yon
    0.07
    له
    0.06
     }
↵
↵
↵
    0.06
    .EX
    0.06
     clinical
    0.06
     О
    0.06
     packing
    0.06
     里
    0.06
    _ERRORS
    0.06
    Act Density 0.000%

    No Known Activations