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

    Neuronpedia

    INDEX
    Explanations

    confirm

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     West
    -0.07
    玩
    -0.07
     plaza
    -0.07
    348
    -0.07
    West
    -0.07
     Mutable
    -0.07
     groundwork
    -0.07
    Location
    -0.06
    Vect
    -0.06
    ViewSet
    -0.06
    POSITIVE LOGITS
     confirmed
    0.12
     confirming
    0.12
     confirm
    0.10
     confirmation
    0.10
    .confirm
    0.09
     Confirm
    0.09
    irma
    0.09
    confirm
    0.08
     confirms
    0.08
     Confirmation
    0.08
    Act Density 0.013%

    No Known Activations