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

    Neuronpedia

    INDEX
    Explanations

    acknowledging bravery

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gemüt
    0.73
     sundry
    0.72
     enjoyable
    0.71
     재미
    0.70
    ymptotic
    0.69
     abundances
    0.69
     fun
    0.68
     euphoria
    0.68
     sumptuous
    0.67
     তৃণমূল
    0.67
    POSITIVE LOGITS
     brave
    1.19
     courage
    1.12
     courageous
    1.11
     bravery
    1.08
     bravely
    0.98
     brav
    0.85
     Courage
    0.85
    勇敢
    0.84
     बहादुर
    0.77
     strength
    0.75
    Act Density 0.390%

    No Known Activations