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

    Neuronpedia

    INDEX
    Explanations

    shipment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bus
    -0.07
     потім
    -0.07
    =""><
    -0.06
     stresses
    -0.06
     maintain
    -0.06
     dwind
    -0.06
    伝
    -0.06
     succès
    -0.06
     award
    -0.06
     varying
    -0.06
    POSITIVE LOGITS
     braz
    0.07
     Fancy
    0.07
    "strings
    0.06
     packing
    0.06
    ได
    0.06
    (beta
    0.06
     tang
    0.06
     Нав
    0.06
    ,',
    0.06
     MyClass
    0.06
    Act Density 0.000%

    No Known Activations