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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     truth
    -0.07
    .table
    -0.07
    314
    -0.06
     moon
    -0.06
     Dylan
    -0.06
     beaucoup
    -0.06
    优秀
    -0.06
     erg
    -0.06
     violet
    -0.06
    uit
    -0.06
    POSITIVE LOGITS
     :)↵
    0.07
    =''):↵
    0.07
    .")↵
    0.06
    ...↵
    0.06
     Supplement
    0.06
     ма
    0.06
    الد
    0.06
    ısında
    0.06
    .setBackground
    0.06
    -tone
    0.06
    Act Density 0.001%

    No Known Activations