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

    Neuronpedia

    INDEX
    Explanations

    but

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    거리
    -0.07
    _contrib
    -0.07
    @Entity
    -0.07
     woo
    -0.07
     정도
    -0.07
    רגע
    -0.07
     onc
    -0.07
    .Localization
    -0.07
     hog
    -0.07
    /System
    -0.07
    POSITIVE LOGITS
     `$
    0.08
    .They
    0.07
     People
    0.06
    (||
    0.06
    js
    0.06
    ologists
    0.06
    只
    0.06
    _instances
    0.06
     Thousands
    0.06
     className
    0.06
    Act Density 0.001%

    No Known Activations