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

    Neuronpedia

    INDEX
    Explanations

    adverbs ending clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ര്‍
    0.32
    <unused988>
    0.31
    ால்
    0.29
     नेम
    0.29
    ಂತಿ
    0.28
    蓿
    0.28
    ანი
    0.27
    ർ
    0.27
    ールの
    0.27
    ोग्राफी
    0.27
    POSITIVE LOGITS
    पणे
    0.38
    aisesti
    0.38
     falando
    0.36
     hablando
    0.34
    ue
    0.34
     tanpa
    0.33
    i
    0.32
     senza
    0.32
    ji
    0.31
    9
    0.31
    Act Density 0.008%

    No Known Activations