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

    Neuronpedia

    INDEX
    Explanations

    Code abbreviations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     BinaryTree
    -0.07
    .TIM
    -0.07
    ưng
    -0.06
     typeId
    -0.06
     Це
    -0.06
    ander
    -0.06
     smlou
    -0.06
    ่าว
    -0.06
     BOOL
    -0.06
    -eye
    -0.06
    POSITIVE LOGITS
     );↵
    0.06
     Trade
    0.06
    -books
    0.06
     rhyme
    0.06
    .).↵↵
    0.06
    Late
    0.06
    ');↵↵
    0.06
    weet
    0.06
     prom
    0.06
    atif
    0.06
    Act Density 0.054%

    No Known Activations