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

    Neuronpedia

    INDEX
    Explanations

    breakdown of why

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused398>
    0.57
    <unused358>
    0.56
    <unused639>
    0.55
    <unused2015>
    0.53
    <unused1074>
    0.52
    अधिक
    0.52
    <unused657>
    0.51
    <unused1092>
    0.51
     berharap
    0.51
    <unused254>
    0.51
    POSITIVE LOGITS
    0.58
    )
    0.58
     (
    0.50
    ),
    0.48
    ))
    0.47
     +
    0.45
     หรือ
    0.43
     অথবা
    0.43
    ):
    0.43
    ')
    0.43
    Act Density 0.143%

    No Known Activations