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

    Neuronpedia

    INDEX
    Explanations

    is/are described

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sebuah
    1.51
     একটি
    1.24
    Another
    1.22
    ഒരു
    1.20
     μια
    1.20
     isang
    1.14
     sejumlah
    1.14
    一个
    1.11
    一個
    1.10
     suatu
    1.08
    POSITIVE LOGITS
     conducive
    1.23
     popularly
    1.15
     commonly
    1.14
     meant
    1.14
     worthy
    1.13
     worth
    1.09
     deemed
    1.05
     relevant
    1.03
     bothering
    1.01
     deserving
    1.01
    Act Density 0.119%

    No Known Activations