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

    Neuronpedia

    INDEX
    Explanations

    say "ley"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     조선
    -0.07
    积
    -0.07
     signaled
    -0.07
    และการ
    -0.07
    submenu
    -0.06
     Vapor
    -0.06
    *);↵↵
    -0.06
     Culture
    -0.06
    Educ
    -0.06
     Чтобы
    -0.06
    POSITIVE LOGITS
     mole
    0.07
     prima
    0.06
     fend
    0.06
     expenses
    0.06
     ruk
    0.06
     hacking
    0.06
     creators
    0.06
    iglia
    0.06
    .Created
    0.06
     itemView
    0.06
    Act Density 0.044%

    No Known Activations