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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (so
    -0.07
     الوف
    -0.07
     Roy
    -0.07
    WG
    -0.07
    .getUserName
    -0.06
     sam
    -0.06
     roughly
    -0.06
    ServiceImpl
    -0.06
    automation
    -0.06
    Mom
    -0.06
    POSITIVE LOGITS
    Rights
    0.07
     },
↵
    0.06
    告
    0.06
     rights
    0.06
    <p
    0.06
     debit
    0.06
     Acting
    0.06
    overlap
    0.06
     distort
    0.06
     dilation
    0.06
    Act Density 0.047%

    No Known Activations