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

    Neuronpedia

    INDEX
    Explanations

    outer apply

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     পল্ল
    0.52
    忶
    0.47
    ᄈ
    0.44
    <unused244>
    0.44
     अवस्थ
    0.44
    䚲
    0.44
    是因为
    0.43
    пень
    0.43
    编辑器
    0.43
    tDBOutput
    0.42
    POSITIVE LOGITS
    an
    0.54
     no
    0.46
     vir
    0.45
     a
    0.44
      
    0.43
    ’
    0.42
    amino
    0.42
       
    0.42
     protein
    0.42
    ado
    0.40
    Act Density 0.006%

    No Known Activations