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

    Neuronpedia

    INDEX
    Explanations

    guide, engineer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Guide
    -0.94
    Guide
    -0.92
    guide
    -0.84
     GUIDE
    -0.79
    GUIDE
    -0.70
    UnsafeEnabled
    -0.63
     guide
    -0.62
     Engineer
    -0.56
     NSCoder
    -0.55
    ,:,
    -0.53
    POSITIVE LOGITS
     unknownFields
    0.60
    SuppressLint
    0.57
    CopyWith
    0.55
    DrawerToggle
    0.54
    🏽
    0.54
    🏾
    0.53
     WebDriverWait
    0.53
     CreateTagHelper
    0.52
    MetaType
    0.52
    ldc
    0.50
    Act Density 0.076%

    No Known Activations