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

    Neuronpedia

    INDEX
    Explanations

    users and automation

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     WENO
    0.58
     AIAA
    0.57
     nltk
    0.57
     NSTX
    0.56
     golongan
    0.55
     Eurostile
    0.54
     Topeka
    0.54
     postseason
    0.53
     Untersuchungen
    0.53
     MALDI
    0.53
    POSITIVE LOGITS
    user
    0.53
    users
    0.52
    User
    0.49
     功能
    0.48
     users
    0.47
    Automation
    0.47
     用户
    0.46
    Users
    0.44
     개발
    0.44
    Security
    0.43
    Act Density 0.393%

    No Known Activations