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

    Neuronpedia

    INDEX
    Explanations

    high Fidelity, school, lighting, Lords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    적으로
    0.89
     LMS
    0.78
    र्डर
    0.78
    スペック
    0.76
    젹
    0.75
    ized
    0.75
     tinge
    0.74
    وتی
    0.74
    的に
    0.74
    力的
    0.73
    POSITIVE LOGITS
    school
    1.10
    ness
    1.05
    lighting
    0.99
    nesses
    0.97
     noon
    0.88
    School
    0.83
    स्कूल
    0.82
    Enough
    0.81
    schools
    0.79
     impossible
    0.79
    Act Density 0.072%

    No Known Activations