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

    Neuronpedia

    INDEX
    Explanations

    Events in various locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     landings
    -0.87
    webElementXpaths
    -0.87
     baths
    -0.84
    lably
    -0.82
     hearers
    -0.81
     quarries
    -0.79
     burners
    -0.76
    :✨
    -0.76
     craters
    -0.76
    InputBorder
    -0.75
    POSITIVE LOGITS
     to
    0.67
     in
    0.58
     made
    0.57
    olver
    0.54
     on
    0.52
     are
    0.51
     can
    0.51
     here
    0.49
     with
    0.47
     among
    0.46
    Act Density 0.166%

    No Known Activations