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

    Neuronpedia

    INDEX
    Explanations

    URLs and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mutations
    -0.06
    ALL
    -0.06
     Yup
    -0.06
     Online
    -0.06
     Speaker
    -0.06
    Dto
    -0.06
    (py
    -0.06
     authoritarian
    -0.06
     děl
    -0.06
     breath
    -0.06
    POSITIVE LOGITS
     сторін
    0.06
     noc
    0.06
     freedoms
    0.06
    ()<
    0.06
    /books
    0.06
    .fb
    0.06
    (sp
    0.06
     člově
    0.06
     Marathon
    0.06
     первой
    0.06
    Act Density 0.015%

    No Known Activations