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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions with variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     သူ့
    0.44
    .
    0.44
     ဒါ
    0.43
    قیه
    0.41
     Unless
    0.40
     αλλά
    0.38
     သူမ
    0.38
     begitu
    0.38
     butyl
    0.38
    okra
    0.37
    POSITIVE LOGITS
    </b>
    0.39
    \
    0.37
     १५
    0.36
    }
    0.36
    ﭜ
    0.36
     Swami
    0.35
    裒
    0.35
    }$
    0.35
    ๅ
    0.35
    ，
    0.35
    Act Density 0.041%

    No Known Activations