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

    Neuronpedia

    INDEX
    Explanations

    Mistral 7B

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     este
    0.42
     Ў
    0.39
     Bezug
    0.36
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.36
     determination
    0.36
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.36
     DataTable
    0.36
     Goog
    0.35
    าร
    0.35
     spac
    0.35
    POSITIVE LOGITS
    //////
    0.39
     বাঙ্গাল
    0.38
    _="
    0.38
    .«
    0.38
    ্স্ট
    0.37
    __."
    0.36
     보통
    0.36
    }--\
    0.36
     شد
    0.36
    வீ
    0.36
    Act Density 0.026%

    No Known Activations