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

    Neuronpedia

    INDEX
    Explanations

    opening of accounts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Mâc
    0.44
    ୬
    0.42
    也都
    0.42
    Asimismo
    0.42
     levelled
    0.42
    সন
    0.40
     înviat
    0.39
    孅
    0.39
     tiež
    0.38
    汆
    0.38
    POSITIVE LOGITS
    ¹
    0.49
     unexpectedly
    0.46
    1
    0.43
     A
    0.42
     Microsoft
    0.41
     Dec
    0.41
    %
    0.41
     perfect
    0.41
     No
    0.40
     step
    0.40
    Act Density 0.001%

    No Known Activations