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

    Neuronpedia

    INDEX
    Explanations

    scientific discoveries and observations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     omnichannel
    0.59
    运营
    0.57
    वर्तमान
    0.54
    供应链
    0.54
    戙
    0.53
    权限
    0.51
     سافٹ
    0.51
    StarCore
    0.50
    运维
    0.50
    嶈
    0.50
    POSITIVE LOGITS
     discoveries
    1.05
     observations
    1.02
     experiments
    0.97
     discovered
    0.96
     discovery
    0.94
     Observations
    0.87
     pioneering
    0.87
    discover
    0.86
     investigations
    0.86
    発見
    0.85
    Act Density 0.049%

    No Known Activations