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

    Neuronpedia

    INDEX
    Explanations

    interested in learning more

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     intento
    0.43
    хам
    0.40
    結果
    0.39
     ""){
    0.39
    $$
    0.39
    !);
    0.39
    нія
    0.38
    та
    0.38
     que
    0.38
    !")
    0.38
    POSITIVE LOGITS
    DomainMask
    0.46
    繼續
    0.43
     UserModel
    0.42
    继续
    0.39
    മൂഹ
    0.39
    िरपेक्ष
    0.39
    েল
    0.38
    觊
    0.38
     கொண்டே
    0.38
    മാണ
    0.37
    Act Density 0.003%

    No Known Activations