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

    Neuronpedia

    INDEX
    Explanations

    Code syntax

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    employees
    -0.07
    lobals
    -0.06
    国家
    -0.06
    hung
    -0.06
     Ops
    -0.06
    choice
    -0.06
    Processor
    -0.06
     conservatism
    -0.06
    shape
    -0.06
     photographers
    -0.06
    POSITIVE LOGITS
    uenta
    0.07
     cont
    0.06
     LIC
    0.06
     removing
    0.06
    avorite
    0.06
    ovně
    0.06
     GANG
    0.06
     ölçüde
    0.06
     fila
    0.06
    ippi
    0.06
    Act Density 0.016%

    No Known Activations