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

    Neuronpedia

    INDEX
    Explanations

    help you write

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     কিছু
    0.64
    ні
    0.50
    miştir
    0.50
     enkele
    0.49
    iser
    0.49
     некоторых
    0.48
     latéral
    0.47
    保证金
    0.47
     criado
    0.46
    ní
    0.46
    POSITIVE LOGITS
     services
    0.65
     servicios
    0.65
     услуги
    0.62
     서비스를
    0.58
     Services
    0.57
     customized
    0.56
     Specialists
    0.56
     tailored
    0.56
    ק
    0.56
     servizi
    0.54
    Act Density 0.411%

    No Known Activations