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

    Neuronpedia

    INDEX
    Explanations

    brackets, parentheses, quotes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    át
    -0.07
     Material
    -0.07
     Werk
    -0.06
    oracle
    -0.06
    альные
    -0.06
    ât
    -0.06
    樂
    -0.06
    ीएस
    -0.06
     loops
    -0.06
     seç
    -0.06
    POSITIVE LOGITS
     ):↵
    0.07
    と思
    0.07
     Aspect
    0.06
     memorable
    0.06
     dific
    0.06
     Contributor
    0.06
     stop
    0.06
     waged
    0.06
    .gamma
    0.06
    !!!
    0.06
    Act Density 0.027%

    No Known Activations