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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WindowTitle
    0.66
    originalname
    0.64
    Sne
    0.64
    deleteAll
    0.62
     Clayton
    0.62
    ︡
    0.62
    DefaultFor
    0.61
    maximum
    0.61
    organisms
    0.61
    Jackson
    0.61
    POSITIVE LOGITS
     service
    2.79
     Service
    2.54
    服务
    2.45
     servicio
    2.43
    サービス
    2.41
     services
    2.37
    Service
    2.33
     서비스
    2.32
    service
    2.30
    服務
    2.26
    Act Density 0.005%

    No Known Activations