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

    Neuronpedia

    INDEX
    Explanations

    mentioning specific past times

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fussy
    0.45
    因
    0.40
     因
    0.40
    路径
    0.38
     пъ
    0.38
     или
    0.38
     требуют
    0.38
     thresholds
    0.38
     усіх
    0.37
     với
    0.37
    POSITIVE LOGITS
    當時
    0.60
    当时
    0.51
     damals
    0.48
    ptt
    0.47
    ਹਾ
    0.47
     damal
    0.47
     তখন
    0.46
    മായിരുന്നു
    0.44
    Colomb
    0.44
     પોલીસે
    0.44
    Act Density 0.001%

    No Known Activations