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

    Neuronpedia

    INDEX
    Explanations

    age and years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kết
    0.39
    chh
    0.39
     ፈ
    0.38
     flick
    0.38
     pah
    0.38
    พลิ
    0.37
    ouest
    0.36
     vamp
    0.36
    Accessor
    0.36
     crest
    0.36
    POSITIVE LOGITS
    아야
    0.50
    어야
    0.45
     हुसैन
    0.42
     Increasingly
    0.39
    स्ट्रेशन
    0.39
     голова
    0.38
    셔야
    0.38
     ¹
    0.37
     こんな
    0.37
     রোড
    0.37
    Act Density 0.027%

    No Known Activations