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

    Neuronpedia

    INDEX
    Explanations

    rare human unique instances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     نقدم
    0.48
    Wells
    0.45
     تحتاج
    0.45
     personalizar
    0.44
     minha
    0.44
     personnaliser
    0.40
    ایت
    0.40
    فع
    0.39
     tratamento
    0.39
    潤
    0.38
    POSITIVE LOGITS
     equality
    0.53
    в
    0.52
     равно
    0.51
     Gleich
    0.50
     ⿱
    0.47
    affaires
    0.47
     ද
    0.46
     equitable
    0.46
     égale
    0.46
     затруд
    0.46
    Act Density 0.007%

    No Known Activations