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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     titleLabel
    -0.07
    293
    -0.07
    ')){↵
    -0.07
    /gtest
    -0.07
    ){//
    -0.07
    etes
    -0.07
    204
    -0.06
     Liberals
    -0.06
     Jay
    -0.06
     FormControl
    -0.06
    POSITIVE LOGITS
     posição
    0.07
    кою
    0.06
     consequently
    0.06
    IAN
    0.06
     subparagraph
    0.06
    ();↵↵
    0.06
    τύ
    0.06
    صة
    0.06
     ε�
    0.06
    .BackgroundImageLayout
    0.06
    Act Density 0.035%

    No Known Activations