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

    Neuronpedia

    INDEX
    Explanations

    Common English words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ience
    -0.06
     republiky
    -0.06
    ้ก
    -0.06
    Cnt
    -0.06
    чу
    -0.06
    En
    -0.06
     ци
    -0.06
    석
    -0.06
    -0.06
     fever
    -0.06
    POSITIVE LOGITS
    PHY
    0.07
    ，一
    0.06
    URITY
    0.06
     taxes
    0.06
     WOW
    0.06
     Vernon
    0.06
    TriState
    0.06
    mour
    0.06
    %^
    0.06
    738
    0.06
    Act Density 0.000%

    No Known Activations