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

    Neuronpedia

    INDEX
    Explanations

    instantiating new objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    密的
    0.53
    createNew
    0.46
     созда
    0.46
     создания
    0.46
    密
    0.45
     Cria
    0.43
    create
    0.43
    created
    0.43
     створення
    0.43
     астро
    0.42
    POSITIVE LOGITS
     ละ
    0.42
     nuevas
    0.39
     nuove
    0.39
     Berth
    0.39
     Grand
    0.39
     గ
    0.39
     constitu
    0.39
     Toda
    0.38
     bat
    0.38
    ibilità
    0.38
    Act Density 0.006%

    No Known Activations