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

    Neuronpedia

    INDEX
    Explanations

    questions and instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ​​
    0.55
     XNUMX
    0.50
    ​​
    0.45
     ENS
    0.44
     Z
    0.43
    Ensure
    0.43
     Ensure
    0.43
     zal
    0.42
     voi
    0.42
     crores
    0.42
    POSITIVE LOGITS
     İstanbul
    0.52
     ترکی
    0.46
    İstanbul
    0.46
     anybody
    0.45
     الترك
    0.44
     लाहिड़ी
    0.44
     governmental
    0.43
     তুরস্ক
    0.42
     Турции
    0.42
    turkish
    0.41
    Act Density 0.002%

    No Known Activations