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

    Neuronpedia

    INDEX
    Explanations

    memory barriers and visibility

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mc
    -0.07
     Mitar
    -0.07
    ubbles
    -0.07
     Functor
    -0.07
    Operators
    -0.07
    oters
    -0.06
     О
    -0.06
    Play
    -0.06
    osl
    -0.06
    covering
    -0.06
    POSITIVE LOGITS
    "",↵
    0.08
     แหล
    0.06
     shady
    0.06
    301
    0.06
    车
    0.06
    _clock
    0.06
    levard
    0.06
     filmy
    0.06
    自己的
    0.06
    onso
    0.06
    Act Density 0.066%

    No Known Activations