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

    Neuronpedia

    INDEX
    Explanations

    getters and setters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    чин
    0.42
     কখনোই
    0.40
    ான
    0.39
    Wax
    0.39
    хом
    0.38
    厥
    0.37
    கோ
    0.37
     النفس
    0.36
    依托
    0.36
    有机
    0.36
    POSITIVE LOGITS
     constructor
    0.46
    gmail
    0.42
     Init
    0.41
     editor
    0.40
    iend
    0.38
     getClass
    0.38
     类
    0.37
    ;
    0.37
     setter
    0.37
     관리
    0.37
    Act Density 0.006%

    No Known Activations