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

    Neuronpedia

    INDEX
    Explanations

    up

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    オリ
    -0.07
    .hero
    -0.07
    Empleado
    -0.06
    ﻨ
    -0.06
     cinema
    -0.06
     بسی
    -0.06
    できる
    -0.06
     трьох
    -0.06
     یافته
    -0.06
    fn
    -0.06
    POSITIVE LOGITS
     meetup
    0.11
     opt
    0.06
    .utf
    0.06
    cout
    0.06
     Volunteer
    0.06
     Surf
    0.06
    -ts
    0.06
    uetooth
    0.06
    -connect
    0.06
    χεί
    0.06
    Act Density 0.002%

    No Known Activations