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

    Neuronpedia

    INDEX
    Explanations

    grades or scores

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ان
    0.88
    鿓
    0.84
    ار
    0.82
    ｆ
    0.82
    𝕤
    0.79
    د
    0.75
    älte
    0.75
    ко
    0.73
    你有
    0.72
     inhom
    0.72
    POSITIVE LOGITS
     courageous
    0.86
     cherished
    0.79
     vulnerabilities
    0.73
     brave
    0.73
     çap
    0.73
     captivity
    0.73
     who
    0.72
     humana
    0.72
     martyrdom
    0.71
     da
    0.70
    Act Density 0.017%

    No Known Activations