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

    Neuronpedia

    INDEX
    Explanations

    provides or allows

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    使用
    0.38
    ý
    0.34
    applications
    0.33
     sử
    0.32
    łów
    0.32
     utilising
    0.32
    utiliser
    0.32
     applicazioni
    0.31
    陆续
    0.31
    する必要があります
    0.31
    POSITIVE LOGITS
     reminds
    0.66
     reminder
    0.64
     remind
    0.64
     allows
    0.60
     reminders
    0.60
    提醒
    0.59
     reminding
    0.59
     Allows
    0.56
     помогает
    0.55
     provides
    0.55
    Act Density 0.247%

    No Known Activations