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

    Neuronpedia

    INDEX
    Explanations

    Code and file paths

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    する
    -0.07
     dump
    -0.06
    بل
    -0.06
     här
    -0.06
     där
    -0.06
    画
    -0.06
     المللی
    -0.06
     JLabel
    -0.06
    а�
    -0.06
     taxing
    -0.06
    POSITIVE LOGITS
    .Strict
    0.08
    .HttpSession
    0.07
     фін
    0.07
     Ghana
    0.07
     EventEmitter
    0.06
     Homework
    0.06
     dikkat
    0.06
    sak
    0.06
     Россия
    0.06
     localtime
    0.06
    Act Density 0.007%

    No Known Activations