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

    Neuronpedia

    INDEX
    Explanations

    end of turn delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused43>
    0.38
     berpikir
    0.38
    صح
    0.37
    स्तिष्क
    0.37
    क्टेयर
    0.37
    依靠
    0.36
    식회사
    0.36
    甾
    0.36
    पान
    0.36
    只见
    0.36
    POSITIVE LOGITS
     Srin
    0.41
     nominally
    0.40
    }}$.
    0.39
     ostensibly
    0.37
    ]$.
    0.36
     Slovakia
    0.36
     Ideally
    0.35
    পূর্ণ
    0.35
    remarkable
    0.35
    SDD
    0.34
    Act Density 0.002%

    No Known Activations