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

    Neuronpedia

    INDEX
    Explanations

    Lock

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bree
    -0.07
     attributed
    -0.07
     Cyrus
    -0.07
     dří
    -0.07
     plausible
    -0.07
     provincia
    -0.07
    hua
    -0.07
     облі
    -0.07
     jazy
    -0.07
     basis
    -0.07
    POSITIVE LOGITS
     Lock
    0.15
     lock
    0.14
    Lock
    0.13
     locking
    0.13
     locked
    0.13
    lock
    0.12
    LOCK
    0.12
     LOCK
    0.11
    -lock
    0.11
     locks
    0.10
    Act Density 0.013%

    No Known Activations