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

    Neuronpedia

    INDEX
    Explanations

    isolation and loneliness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    لي
    0.39
    owels
    0.38
    cont
    0.38
    DAY
    0.38
    heritage
    0.38
    sea
    0.38
     consci
    0.37
    know
    0.37
     leap
    0.37
    maket
    0.37
    POSITIVE LOGITS
     głównie
    0.57
     服务器
    0.55
     সতর্কতা
    0.54
     całkow
    0.54
     aislamiento
    0.51
     épaisse
    0.50
     Serviços
    0.50
    重新
    0.49
     关闭
    0.49
     用于
    0.49
    Act Density 0.002%

    No Known Activations