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

    Neuronpedia

    INDEX
    Explanations

    nobility

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     investig
    -0.07
    Resp
    -0.07
     psychiat
    -0.06
     psychiatric
    -0.06
     Writer
    -0.06
     numerical
    -0.06
    ethe
    -0.06
    ournament
    -0.06
     máximo
    -0.06
     Predict
    -0.06
    POSITIVE LOGITS
     trailing
    0.07
     blackjack
    0.07
     Друг
    0.06
     أد
    0.06
     MAG
    0.06
    LENGTH
    0.06
    ABCDE
    0.06
    кої
    0.06
     artillery
    0.06
     độ
    0.06
    Act Density 0.017%

    No Known Activations