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

    Neuronpedia

    INDEX
    Explanations

    param

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Diaz
    -0.07
    和
    -0.06
    .Logic
    -0.06
    IPv
    -0.06
     говорить
    -0.06
     Tx
    -0.06
     rocker
    -0.06
    /tags
    -0.06
     pilots
    -0.06
     яс
    -0.06
    POSITIVE LOGITS
    .HOUR
    0.06
    (po
    0.06
    CTIONS
    0.06
     onsite
    0.06
     personalized
    0.06
    addColumn
    0.06
    -wage
    0.06
     ark
    0.06
    medical
    0.06
    視
    0.06
    Act Density 0.002%

    No Known Activations