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

    Neuronpedia

    INDEX
    Explanations

    prominent figures and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Keci
    0.24
     😏
    0.22
    倞
    0.21
     Inquisition
    0.20
    勍
    0.20
    頎
    0.20
     загряз
    0.19
     المرك
    0.19
    夆
    0.19
     अशुभ
    0.18
    POSITIVE LOGITS
     C
    0.18
    C
    0.18
     mantan
    0.18
     G
    0.17
     তৎকালীন
    0.16
     T
    0.16
     R
    0.15
     famously
    0.15
    T
    0.15
     legendary
    0.15
    Act Density 0.053%

    No Known Activations