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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    social
    -0.07
     paylaş
    -0.07
    >|
    -0.06
     trie
    -0.06
     purse
    -0.06
     headed
    -0.06
    ghest
    -0.06
    Topics
    -0.06
     troops
    -0.06
     tribes
    -0.06
    POSITIVE LOGITS
     |--------------------------------------------------------------------------↵
    0.07
     amendments
    0.07
    ладу
    0.07
    験
    0.07
     evaluation
    0.06
    人口
    0.06
     Velocity
    0.06
     กรกฎ
    0.06
     [$
    0.06
    _IMPORT
    0.06
    Act Density 0.001%

    No Known Activations