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

    Neuronpedia

    INDEX
    Explanations

    collusion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    MemoryWarning
    -0.80
    RectangleBorder
    -0.71
    TargetException
    -0.71
    MessageTagHelper
    -0.65
    viewDidLoad
    -0.63
    enumi
    -0.63
    WaitGroup
    -0.62
    \{\\
    -0.61
    MultipartFile
    -0.61
     للمعارف
    -0.60
    POSITIVE LOGITS
     with
    0.52
    ude
    0.52
    hical
    0.47
     agreements
    0.47
    setVerticalGroup
    0.46
     between
    0.45
    Explicit
    0.45
    PreferredItem
    0.45
    Stealth
    0.44
    ched
    0.44
    Act Density 0.001%

    No Known Activations