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

    Neuronpedia

    INDEX
    Explanations

    deal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    +t
    -0.06
     nacional
    -0.06
    �
    -0.06
    こんな
    -0.06
    ày
    -0.06
     Xt
    -0.06
     Challenge
    -0.06
    MAS
    -0.06
     telemetry
    -0.06
    เย
    -0.06
    POSITIVE LOGITS
     generic
    0.07
    ==='
    0.06
     flask
    0.06
    ?>↵↵
    0.06
     NSMutable
    0.06
    �다
    0.06
     etmesi
    0.06
    ebiliriz
    0.06
    ardım
    0.06
    .sorted
    0.06
    Act Density 0.001%

    No Known Activations