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

    Neuronpedia

    INDEX
    Explanations

    could ask for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    นิด
    0.44
     הרב
    0.40
    整体
    0.39
    overall
    0.39
    整體
    0.38
     совсем
    0.38
    ሙሉ
    0.38
     약간
    0.37
     overall
    0.36
    じる
    0.36
    POSITIVE LOGITS
     better
    0.98
    更好的
    0.88
     bättre
    0.87
     worse
    0.83
     lepiej
    0.82
    better
    0.82
     bessere
    0.82
     BETTER
    0.79
     leps
    0.79
    更好
    0.78
    Act Density 0.005%

    No Known Activations