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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ّل
    -0.07
     Theft
    -0.07
    imu
    -0.07
    ject
    -0.06
    Layout
    -0.06
    �
    -0.06
     CCTV
    -0.06
     Manuals
    -0.06
     Sounds
    -0.06
    STRUCT
    -0.06
    POSITIVE LOGITS
    ondere
    0.08
     vill
    0.07
    ký
    0.07
    .est
    0.06
    biên
    0.06
    jsx
    0.06
    凝
    0.06
    detach
    0.06
    encv
    0.06
    ในการ
    0.06
    Act Density 0.060%

    No Known Activations