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

    Neuronpedia

    INDEX
    Explanations

    book introductions and history sections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ：
    0.50
    ():
    0.43
    :
    0.42
    __:
    0.42
    :‏
    0.41
    ามารถ
    0.40
    ]:
    0.37
    ：“
    0.37
    ：《
    0.36
    FICATION
    0.36
    POSITIVE LOGITS
     for
    0.44
     nejen
    0.43
     для
    0.40
     reinvent
    0.40
     niezwy
    0.38
     برای
    0.37
     стреми
    0.37
    Для
    0.36
    для
    0.35
     новой
    0.35
    Act Density 0.053%

    No Known Activations