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

    Neuronpedia

    INDEX
    Explanations

    Vector calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Corey
    -0.07
     Berm
    -0.07
    Lou
    -0.07
     ков
    -0.06
     GAR
    -0.06
    Reservation
    -0.06
     complication
    -0.06
    068
    -0.06
    Ni
    -0.06
    CAR
    -0.06
    POSITIVE LOGITS
    (Api
    0.07
    (DataType
    0.07
    σία
    0.07
     byla
    0.06
    (::
    0.06
     Burger
    0.06
     Times
    0.06
    .BadRequest
    0.06
    ѕ
    0.06
     și
    0.06
    Act Density 0.044%

    No Known Activations