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

    Neuronpedia

    INDEX
    Explanations

    employee benefits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dispens
    0.43
    獾
    0.42
     spacerItem
    0.41
    缛
    0.41
     我们
    0.41
    幂
    0.41
    댓글
    0.41
    涣
    0.40
    豢
    0.40
    剿
    0.40
    POSITIVE LOGITS
    라서
    0.48
     समीर
    0.47
    systems
    0.46
    are
    0.44
    oda
    0.44
    これが
    0.44
    어
    0.44
     Briefly
    0.43
     ਇਹ
    0.43
    type
    0.42
    Act Density 0.000%

    No Known Activations