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

    Neuronpedia

    INDEX
    Explanations

    modification

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <Transaction
    -0.07
     fot
    -0.07
    .px
    -0.07
    、日本
    -0.06
    r
    -0.06
    .sat
    -0.06
    trak
    -0.06
    ']])↵
    -0.06
     animation
    -0.06
    enter
    -0.06
    POSITIVE LOGITS
    (mark
    0.07
    696
    0.06
    だよ
    0.06
     Flush
    0.06
    ่อ
    0.06
    allocation
    0.06
     {};
↵
    0.06
    WATCH
    0.06
    ग
    0.06
    >'.↵
    0.06
    Act Density 0.001%

    No Known Activations