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

    Neuronpedia

    INDEX
    Explanations

    have / had negations of abstract states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     telah
    0.50
    =
    0.45
     đã
    0.44
    によって
    0.40
     became
    0.39
    获得了
    0.38
     kreeg
    0.38
    完成了
    0.38
    उन्होंने
    0.36
     almış
    0.36
    POSITIVE LOGITS
     nightmares
    0.61
     shortcomings
    0.57
     hiccups
    0.55
     limitations
    0.55
     failings
    0.55
     suspicions
    0.54
     repercussions
    0.54
     problems
    0.52
     pretensions
    0.52
     trouble
    0.50
    Act Density 0.178%

    No Known Activations