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

    Neuronpedia

    INDEX
    Explanations

    authorization

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    梦
    -0.08
    눱
    -0.08
    �
    -0.07
    sun
    -0.07
    stable
    -0.07
    _unix
    -0.07
    .Logger
    -0.06
    ежду
    -0.06
    動き
    -0.06
    烦恼
    -0.06
    POSITIVE LOGITS
     PIC
    0.08
     Authorization
    0.07
    مواد
    0.07
     Grants
    0.07
     осуществля
    0.07
     обязательно
    0.07
    充足的
    0.07
     RAID
    0.07
    䂮
    0.07
    _ER
    0.07
    Act Density 0.007%

    No Known Activations