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

    Neuronpedia

    INDEX
    Explanations

    technical error or warning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fluctuations
    0.39
     emin
    0.39
     morphological
    0.37
     proletariat
    0.36
     incisions
    0.36
     subcontract
    0.35
     gilt
    0.35
     processos
    0.34
     fibroblasts
    0.34
     diversify
    0.34
    POSITIVE LOGITS
    Sandy
    0.41
     Bagley
    0.38
    SegmentInfo
    0.37
    疯
    0.36
     주고
    0.35
    שת
    0.34
    izer
    0.33
    Bag
    0.33
    了一个
    0.33
    了一個
    0.33
    Act Density 0.000%

    No Known Activations