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

    Neuronpedia

    INDEX
    Explanations

    customer satisfaction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Occupational
    -0.07
    fits
    -0.07
     Monetary
    -0.07
    .getTitle
    -0.06
    -ticket
    -0.06
    protocol
    -0.06
     highway
    -0.06
     frag
    -0.06
    -income
    -0.06
    .ca
    -0.06
    POSITIVE LOGITS
     вред
    0.06
     وع
    0.06
    /MIT
    0.06
    ทำให
    0.06
    以外
    0.06
     درب
    0.06
     đôi
    0.06
    했습니다
    0.06
     соответ
    0.06
    ahtar
    0.06
    Act Density 0.065%

    No Known Activations