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

    Neuronpedia

    INDEX
    Explanations

    fun and exciting activities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     بزرگ
    -0.07
    Powered
    -0.07
    обходим
    -0.06
     м
    -0.06
     Greek
    -0.06
    有一
    -0.06
     Fashion
    -0.06
    담
    -0.06
     Deus
    -0.06
    /dr
    -0.06
    POSITIVE LOGITS
     nin
    0.06
    絶
    0.06
    Sep
    0.06
     bounce
    0.06
     různé
    0.06
    numer
    0.06
     serializers
    0.06
     hangi
    0.06
     Hans
    0.06
     ConfigureServices
    0.06
    Act Density 0.205%

    No Known Activations