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

    Neuronpedia

    INDEX
    Explanations

    actions to explain or make

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     żeby
    0.51
     чтобы
    0.44
     bằng
    0.43
     để
    0.42
     אם
    0.42
     путем
    0.41
     때문에
    0.41
     对于
    0.41
     ক্ষেত্রেই
    0.41
     substances
    0.40
    POSITIVE LOGITS
    Cadastro
    0.40
     odpowied
    0.38
    Gambar
    0.38
    ASX
    0.37
    스트
    0.37
    анд
    0.37
    גי
    0.36
     the
    0.35
    र्ने
    0.35
    更
    0.35
    Act Density 0.355%

    No Known Activations