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

    Neuronpedia

    INDEX
    Explanations

    explaining what it is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    wet
    0.67
     ошиб
    0.67
    軽量
    0.65
    only
    0.65
    Mari
    0.64
    Only
    0.64
    Wet
    0.63
    列表中
    0.63
    urities
    0.63
    List
    0.62
    POSITIVE LOGITS
     doing
    1.88
     Doing
    1.68
    Doing
    1.51
     accomplishing
    1.42
    doing
    1.41
     accomplish
    1.34
     do
    1.34
     accomplishes
    1.30
     accomplished
    1.30
     entailed
    1.27
    Act Density 0.619%

    No Known Activations