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

    Neuronpedia

    INDEX
    Explanations

    common text beginnings

    np_acts-logits-general · gemini-2.5-flash-lite

    (no pattern found)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ми
    1.06
    Τ
    0.97
    Nome
    0.96
    Еще
    0.94
    padă
    0.92
     Еще
    0.88
    Toplam
    0.88
    UserDetails
    0.87
    Cidade
    0.87
    Một
    0.86
    POSITIVE LOGITS
    ↵↵
    1.67
    o
    1.67
    ar
    1.54
    er
    1.44
    ing
    1.42
    ation
    1.41
    ة
    1.37
    ed
    1.30
    a
    1.30
    ide
    1.23
    Act Density 0.003%

    No Known Activations