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

    Neuronpedia

    INDEX
    Explanations

    moral reasoning and dilemmas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    सर्व
    0.42
    MatContext
    0.41
    MyDrive
    0.39
    ชนิด
    0.38
     Versch
    0.37
     মিথ
    0.36
    Kc
    0.36
     কিল
    0.36
    ларга
    0.35
     রাশি
    0.35
    POSITIVE LOGITS
     mor
    0.79
     morals
    0.75
     мора
    0.74
     Mor
    0.71
     morality
    0.71
    Mor
    0.68
     moral
    0.68
    mor
    0.68
     MOR
    0.67
     morales
    0.65
    Act Density 0.015%

    No Known Activations