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

    Neuronpedia

    INDEX
    Explanations

    abstract methods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Арх
    -0.06
     상
    -0.06
     Marilyn
    -0.06
    .contract
    -0.06
     vlád
    -0.06
     Ban
    -0.06
     Suzanne
    -0.06
     Velocity
    -0.06
     Retrieved
    -0.06
    ancode
    -0.06
    POSITIVE LOGITS
    #,
    0.07
     thăm
    0.07
    _ur
    0.07
    :list
    0.07
     fung
    0.06
    \Input
    0.06
    -May
    0.06
    овала
    0.06
    ={}
    0.06
     impecc
    0.06
    Act Density 0.040%

    No Known Activations