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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sew
    -0.06
     Anton
    -0.06
    ($.
    -0.06
     Fat
    -0.06
     Gareth
    -0.06
     shim
    -0.06
     intake
    -0.06
    NA
    -0.06
     annotation
    -0.06
     Ton
    -0.06
    POSITIVE LOGITS
     buzz
    0.07
    anker
    0.07
    ющими
    0.06
    spinner
    0.06
     Newtown
    0.06
    คโนโลย
    0.06
    úng
    0.06
    Colors
    0.06
    yntax
    0.06
    атели
    0.06
    Act Density 0.000%

    No Known Activations