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

    Neuronpedia

    INDEX
    Explanations

    Code/math notation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    租车
    -0.07
     Args
    -0.07
     Sweep
    -0.07
    年来
    -0.07
    ijd
    -0.07
     lending
    -0.06
    German
    -0.06
    -te
    -0.06
    ValidateAntiForgeryToken
    -0.06
     Payments
    -0.06
    POSITIVE LOGITS
     ghost
    0.07
     vanished
    0.07
    .Position
    0.07
    保持着
    0.07
     powstał
    0.06
     Gray
    0.06
    ,res
    0.06
     comeback
    0.06
    =?";↵
    0.06
    放到
    0.06
    Act Density 0.042%

    No Known Activations