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

    Neuronpedia

    INDEX
    Explanations

    image width

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Say
    -0.07
     managers
    -0.07
     guy
    -0.07
     Thinking
    -0.06
     polynomial
    -0.06
     Token
    -0.06
    Software
    -0.06
     theme
    -0.06
    	top
    -0.06
    -star
    -0.06
    POSITIVE LOGITS
     испыт
    0.06
    ②
    0.06
     Yol
    0.06
     klin
    0.06
    =====
    0.06
    LER
    0.06
    λογ
    0.06
     [];
    0.06
     LoginPage
    0.06
     appropri
    0.06
    Act Density 0.010%

    No Known Activations