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

    Neuronpedia

    INDEX
    Explanations

    radar observations and maps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ទ្
    0.56
    ियल
    0.54
     ati
    0.53
     อะไร
    0.52
    мини
    0.52
    чке
    0.51
     przypad
    0.51
     truyền
    0.49
    上限
    0.49
     ani
    0.48
    POSITIVE LOGITS
     الاسلام
    0.51
    ionario
    0.50
     mandated
    0.48
     shard
    0.47
     tossing
    0.47
     ourselves
    0.46
     melting
    0.45
    orphism
    0.45
     virtuous
    0.45
    )]
    0.45
    Act Density 0.001%

    No Known Activations