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

    Neuronpedia

    INDEX
    Explanations

    code comments describe actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     globals
    0.41
     را
    0.41
    pthread
    0.40
    SIBILITIES
    0.40
    找
    0.40
     mutex
    0.39
    权限
    0.39
     inodes
    0.37
    ensible
    0.37
     &&
    0.37
    POSITIVE LOGITS
     Specifies
    0.52
     Tells
    0.52
     Indicates
    0.50
     Puedes
    0.49
     Specify
    0.47
     Use
    0.47
     Passing
    0.46
     указыва
    0.46
    如果你
    0.45
    下記の
    0.45
    Act Density 0.008%

    No Known Activations