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

    Neuronpedia

    INDEX
    Explanations

    Search

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     acknowledgment
    -0.07
    .Persistence
    -0.07
     Goals
    -0.07
     Opening
    -0.07
     COVID
    -0.06
     opening
    -0.06
     ticket
    -0.06
     grading
    -0.06
    ahlen
    -0.06
     Discounts
    -0.06
    POSITIVE LOGITS
     Search
    0.08
    Search
    0.07
     search
    0.06
     rog
    0.06
     رابط
    0.06
     VB
    0.06
    SWEP
    0.06
    -search
    0.06
     groundwork
    0.06
     cb
    0.06
    Act Density 0.002%

    No Known Activations