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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    notification
    -0.07
     dword
    -0.06
     **)&
    -0.06
     Dataset
    -0.06
    воб
    -0.06
    	widget
    -0.06
     fullfile
    -0.06
    .used
    -0.06
    ]->
    -0.06
     Kas
    -0.06
    POSITIVE LOGITS
     scrutin
    0.07
     inflation
    0.06
    очного
    0.06
    anye
    0.06
    μορ
    0.06
    ragen
    0.06
     Engineers
    0.06
     spear
    0.06
     различных
    0.06
    jist
    0.06
    Act Density 0.007%

    No Known Activations