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

    Neuronpedia

    INDEX
    Explanations

    PackageManager

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .writeln
    -0.06
    (entry
    -0.06
    ()))↵↵
    -0.06
    ,");↵
    -0.06
     Dia
    -0.06
     Picture
    -0.06
     />);↵
    -0.06
     мире
    -0.06
     Sandwich
    -0.06
    Depth
    -0.06
    POSITIVE LOGITS
     Ebony
    0.08
    anyl
    0.07
     gi
    0.07
     reacted
    0.07
     TPM
    0.07
     pha
    0.07
     svat
    0.07
     Shuffle
    0.07
    bringing
    0.07
     BI
    0.07
    Act Density 0.002%

    No Known Activations