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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    preferences
    -0.08
    resp
    -0.07
     &:
    -0.07
     Polo
    -0.07
    -desc
    -0.06
    olly
    -0.06
     Allah
    -0.06
     Walls
    -0.06
     JSGlobal
    -0.06
     pt
    -0.06
    POSITIVE LOGITS
    WIN
    0.07
    (json
    0.06
     baiser
    0.06
     ipsum
    0.06
     Abram
    0.06
    ekten
    0.06
     prosecutor
    0.06
     rented
    0.06
    ivre
    0.06
     Brother
    0.06
    Act Density 0.044%

    No Known Activations