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

    Neuronpedia

    INDEX
    Explanations

    special characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    农民
    -0.08
    heroes
    -0.07
    �장
    -0.07
     Infrastructure
    -0.07
     intervention
    -0.07
     средства
    -0.07
     Convenience
    -0.07
     ButterKnife
    -0.06
    蔌
    -0.06
    zers
    -0.06
    POSITIVE LOGITS
    _QU
    0.07
     AE
    0.07
    航空
    0.07
    	It
    0.07
     LEGO
    0.06
    .epsilon
    0.06
    👥
    0.06
    ;;;;;;;;
    0.06
     SK
    0.06
    DateTime
    0.06
    Act Density 0.010%

    No Known Activations