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

    Neuronpedia

    INDEX
    Explanations

    Mutex

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     usize
    -0.07
    (dialog
    -0.07
    />.↵↵
    -0.06
     هر
    -0.06
    "d
    -0.06
    .ReadString
    -0.06
    ("---
    -0.06
    (ok
    -0.06
    afi
    -0.06
    (entry
    -0.06
    POSITIVE LOGITS
    クリ
    0.07
    CASE
    0.07
     �
    0.07
    ��
    0.07
    larımız
    0.07
    iterr
    0.06
     พฤศจ
    0.06
    ynchronized
    0.06
    ників
    0.06
    塔
    0.06
    Act Density 0.003%

    No Known Activations