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

    Neuronpedia

    INDEX
    Explanations

    Vue.js component definitions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     люди
    -0.08
    /url
    -0.08
     weapon
    -0.07
    patrick
    -0.07
    .trans
    -0.07
    Metal
    -0.07
     Celsius
    -0.07
    Crime
    -0.07
    Anne
    -0.07
    愤怒
    -0.07
    POSITIVE LOGITS
    остоя
    0.08
    standen
    0.07
    antino
    0.07
    ستمر
    0.07
     ModelState
    0.07
     slowdown
    0.07
     Hiệp
    0.07
    _RANGE
    0.07
    _friend
    0.06
    chimp
    0.06
    Act Density 0.002%

    No Known Activations