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

    Neuronpedia

    INDEX
    Explanations

    unexpected financial updates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     shitty
    0.86
     inherently
    0.85
     perpetually
    0.83
     کبھی
    0.81
     typically
    0.81
    ALWAYS
    0.81
     chronically
    0.81
     Typically
    0.80
     ALWAYS
    0.79
     altid
    0.79
    POSITIVE LOGITS
     неожидан
    0.86
     diplom
    0.84
     networking
    0.83
    Networking
    0.77
     updates
    0.77
     aggior
    0.76
    趁
    0.76
     nowe
    0.76
    Updates
    0.75
     errands
    0.74
    Act Density 0.020%

    No Known Activations