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

    Neuronpedia

    INDEX
    Explanations

    moving out from

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     warranted
    0.54
    രുവനന്തപു
    0.47
    bibfield
    0.45
     avoided
    0.44
     payers
    0.42
    Ꭼ
    0.42
     internationally
    0.42
    रावट
    0.41
     exhibitors
    0.41
     decked
    0.41
    POSITIVE LOGITS
     Bed
    0.45
    盃
    0.44
     Terrier
    0.43
     서비스를
    0.43
     رفتار
    0.43
    و
    0.43
     ಉತ್ಪ
    0.42
    rie
    0.42
     બીજા
    0.42
    서비스
    0.42
    Act Density 0.002%

    No Known Activations