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

    Neuronpedia

    INDEX
    Explanations

    getters, setters, constructors, data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cemic
    0.41
    Cline
    0.39
     мили
    0.38
    砂
    0.38
     床
    0.37
    ிற்ப
    0.37
    時から
    0.37
    蛉
    0.37
    骖
    0.37
    鉭
    0.36
    POSITIVE LOGITS
     getters
    1.06
    Getter
    1.05
     getter
    0.97
    getter
    0.95
     Getter
    0.91
     setter
    0.89
    Setter
    0.89
     setters
    0.86
     Setter
    0.80
    projectlombok
    0.79
    Act Density 0.006%

    No Known Activations