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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     equipe
    -0.08
     fibonacci
    -0.08
     Android
    -0.07
     billi
    -0.07
     geng
    -0.07
    .DEF
    -0.07
     fél
    -0.07
     rege
    -0.07
     équipe
    -0.07
    )|(
    -0.07
    POSITIVE LOGITS
    额度
    0.10
    payments
    0.10
     भुगतान
    0.10
     распредел
    0.09
     cantidades
    0.09
     башҡ
    0.09
    shipment
    0.09
    paid
    0.09
     веса
    0.09
    Payments
    0.09
    Act Density 0.010%

    No Known Activations