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

    Neuronpedia

    INDEX
    Explanations

    programming questions and data structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     태
    -0.83
     rasp
    -0.79
     VP
    -0.79
     stagn
    -0.79
     withdrawing
    -0.78
     withdraw
    -0.76
    VP
    -0.75
    剩下的
    -0.73
    sistors
    -0.72
    素人
    -0.72
    POSITIVE LOGITS
    userManager
    0.85
    UrlHelper
    0.85
     Gujarati
    0.84
    Panel
    0.80
     Timestamp
    0.76
    locs
    0.76
    Panels
    0.75
    quando
    0.75
     Series
    0.75
    شنامه
    0.75
    Act Density 0.049%

    No Known Activations