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

    Neuronpedia

    INDEX
    Explanations

    perfect

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     leather
    -0.07
    (Default
    -0.07
     円
    -0.07
     Roku
    -0.07
     Multiple
    -0.06
     pipeline
    -0.06
     circuit
    -0.06
     advises
    -0.06
     tai
    -0.06
     svého
    -0.06
    POSITIVE LOGITS
    xBD
    0.07
    bic
    0.06
     εκεί
    0.06
    �
    0.06
    Truth
    0.06
    ONTAL
    0.06
     LogManager
    0.06
    BUTTONDOWN
    0.06
    :Register
    0.06
    шло
    0.06
    Act Density 0.032%

    No Known Activations