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

    Neuronpedia

    INDEX
    Explanations

    we

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Бог
    -0.06
    okud
    -0.06
     PROGRAM
    -0.06
    ฺ
    -0.06
     CPF
    -0.06
    Audit
    -0.06
     configparser
    -0.06
    .DELETE
    -0.06
    atég
    -0.06
    iners
    -0.06
    POSITIVE LOGITS
    -я
    0.07
    religious
    0.07
    _exceptions
    0.07
     Movement
    0.06
    üstü
    0.06
    photo
    0.06
     Neighbor
    0.06
    _DEV
    0.06
    [root
    0.06
    |/
    0.06
    Act Density 0.006%

    No Known Activations