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

    Neuronpedia

    INDEX
    Explanations

    cache/buffer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prohibition
    -0.08
     genealog
    -0.08
     jambes
    -0.08
     Wik
    -0.07
     lak
    -0.07
     সাথে
    -0.07
     شرکت
    -0.07
     jinsi
    -0.07
     Prison
    -0.07
     tele
    -0.07
    POSITIVE LOGITS
    .buffer
    0.17
    buffer
    0.17
     buffer
    0.16
    -buffer
    0.16
    _buffer
    0.16
    	buffer
    0.15
    Buffer
    0.14
    (buffer
    0.14
     buffering
    0.14
    buffers
    0.13
    Act Density 0.009%

    No Known Activations