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

    Neuronpedia

    INDEX
    Explanations

    as much as possible

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     특정
    0.42
     bepaalde
    0.40
    特定の
    0.39
     certains
    0.38
    တစ်
    0.37
    和一个
    0.37
     épa
    0.37
     মাঝারি
    0.37
    क्टर
    0.36
    ENSITY
    0.36
    POSITIVE LOGITS
    尽可能
    1.97
     möglichst
    1.78
    尽量
    1.75
     최대한
    1.73
     максимально
    1.27
    盡
    1.09
     যতটা
    1.05
     όσο
    0.99
     minimize
    0.95
     முடிந்த
    0.95
    Act Density 0.168%

    No Known Activations