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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    enderror
    -0.80
    middels
    -0.77
     myſelf
    -0.70
    Organiser
    -0.68
    ViewFeatures
    -0.66
     surla
    -0.66
    AutoresizingMask
    -0.65
    webElementXpaths
    -0.65
    ​—
    -0.64
    parsedMessage
    -0.63
    POSITIVE LOGITS
     on
    0.58
     passage
    0.49
     needed
    0.48
     direction
    0.47
     game
    0.46
     Little
    0.46
     $
    0.46
    رافی
    0.44
    ¿
    0.44
    DEP
    0.43
    Act Density 0.010%

    No Known Activations