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

    Neuronpedia

    INDEX
    Explanations

    Encoding/formatting issues

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _mod
    -0.08
     Niagara
    -0.07
    -role
    -0.07
     Beginners
    -0.07
    _Tr
    -0.07
    pickle
    -0.07
     السود
    -0.07
    @pytest
    -0.07
    窘
    -0.07
     Mohamed
    -0.06
    POSITIVE LOGITS
    альный
    0.07
     İn
    0.07
     '',↵
    0.06
    背着
    0.06
    %).
    0.06
    ального
    0.06
    `)↵
    0.06
    控制
    0.06
    ++){↵
    0.06
    	open
    0.06
    Act Density 0.053%

    No Known Activations