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

    Neuronpedia

    INDEX
    Explanations

    Earl

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kvm
    -0.06
     thao
    -0.06
    =[];↵
    -0.06
    章
    -0.06
     beberapa
    -0.06
     Azerbaijan
    -0.06
     subsystem
    -0.06
    hidden
    -0.05
    ')):↵
    -0.05
     فريق
    -0.05
    POSITIVE LOGITS
     Earl
    0.07
    ARP
    0.07
    raise
    0.06
    UAL
    0.06
    _TYPED
    0.06
    Warm
    0.06
     bookings
    0.06
    OLT
    0.06
    uffled
    0.06
    outil
    0.06
    Act Density 0.001%

    No Known Activations