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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ]"
    -0.07
    	sub
    -0.07
     classNames
    -0.06
     textField
    -0.06
     我
    -0.06
    Maps
    -0.06
    ']")↵
    -0.06
    你的
    -0.06
     deb
    -0.06
     thereby
    -0.06
    POSITIVE LOGITS
    zia
    0.07
     authoritarian
    0.06
    Ů
    0.06
     italiani
    0.06
    CSV
    0.06
    ΗΜ
    0.06
     sentence
    0.06
     Zag
    0.06
    inz
    0.06
    leşik
    0.06
    Act Density 0.001%

    No Known Activations