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

    Neuronpedia

    INDEX
    Explanations

    direct

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    کور
    -0.07
    墙
    -0.07
    qw
    -0.06
    .cuda
    -0.06
     bakery
    -0.06
     emoji
    -0.06
     surprisingly
    -0.06
    уття
    -0.06
     البي
    -0.06
    くな
    -0.06
    POSITIVE LOGITS
     oleh
    0.07
     Locke
    0.07
     Gateway
    0.06
    .ManyToMany
    0.06
    ,
    0.06
    .
    0.06
    、↵↵
    0.06
    您
    0.06
     marshaller
    0.06
    ,↵↵
    0.06
    Act Density 0.013%

    No Known Activations