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

    Neuronpedia

    INDEX
    Explanations

    concept

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    鲸
    -0.07
    	rd
    -0.07
    �述
    -0.07
    蹿
    -0.07
    .Globalization
    -0.07
     직접
    -0.07
    )i
    -0.07
    雞
    -0.06
    alten
    -0.06
     Sw
    -0.06
    POSITIVE LOGITS
     метро
    0.08
    VEC
    0.07
    роме
    0.07
    שחק
    0.07
    DidAppear
    0.07
    ahrungen
    0.07
     décou
    0.07
    Replacing
    0.07
    ：↵
    0.07
    <stdio
    0.07
    Act Density 0.001%

    No Known Activations