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

    Neuronpedia

    INDEX
    Explanations

    your moral judgments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ujarnya
    0.60
     fitur
    0.58
     herz
    0.53
    AllWindows
    0.51
    请输入
    0.51
     pecahan
    0.50
    属
    0.50
     itu
    0.50
     paréntesis
    0.49
     фактор
    0.49
    POSITIVE LOGITS
     shameful
    0.72
     punishment
    0.71
     magnificent
    0.71
     heaven
    0.68
     mourn
    0.66
     glory
    0.66
     sne
    0.65
     ferocious
    0.64
     cheeks
    0.64
     punished
    0.64
    Act Density 0.000%

    No Known Activations