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

    Neuronpedia

    INDEX
    Explanations

    being locked, locked onto

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PLOAD
    0.59
    صاف
    0.56
    sliced
    0.56
    يد
    0.54
    uhi
    0.53
    x
    0.52
    いますが
    0.52
    paging
    0.52
    ,_-
    0.51
    ുണ്ട്
    0.50
    POSITIVE LOGITS
     lock
    1.36
     locking
    1.31
    锁
    1.23
     Lock
    1.23
     locked
    1.22
     locks
    1.21
     LOCK
    1.17
    锁定
    1.14
     Locking
    1.13
    Lock
    1.12
    Act Density 0.034%

    No Known Activations