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

    Neuronpedia

    INDEX
    Explanations

    disappeared, impact, married, generate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     हॉल
    0.46
     하나
    0.45
     Derechos
    0.45
    ufieurs
    0.43
    oulli
    0.43
    profiss
    0.42
     หนึ่ง
    0.42
     Bumble
    0.42
    clf
    0.42
     Antennes
    0.42
    POSITIVE LOGITS
    in
    0.50
    Market
    0.48
    システムの
    0.48
    ک
    0.47
    ه
    0.47
    f
    0.46
    чатку
    0.46
    SVG
    0.45
    (
    0.45
    systems
    0.44
    Act Density 0.000%

    No Known Activations