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

    Neuronpedia

    INDEX
    Explanations

    conversational phrases and greetings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     albeit
    0.46
     NBC
    0.43
     NPR
    0.41
     Serena
    0.39
     SNC
    0.39
     NGC
    0.38
    Ig
    0.38
     CIR
    0.38
     STAR
    0.38
     RISE
    0.38
    POSITIVE LOGITS
    printDialog
    0.41
     delicios
    0.40
    novation
    0.40
    ındaki
    0.39
    öffentlichung
    0.38
    配置文件
    0.38
    -_
    0.38
     conqu
    0.38
    зг
    0.38
    числе
    0.37
    Act Density 0.004%

    No Known Activations