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

    Neuronpedia

    INDEX
    Explanations

    vocab and grammar

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Detection
    -0.08
    运用
    -0.07
     complained
    -0.07
    \Component
    -0.07
    手段
    -0.07
    科普
    -0.07
    河水
    -0.07
    Put
    -0.07
    낍
    -0.07
    场景
    -0.06
    POSITIVE LOGITS
     starters
    0.06
     lord
    0.06
    added
    0.06
    长沙市
    0.06
     citizen
    0.06
    _LA
    0.06
    _HEADER
    0.06
    grammar
    0.06
    UB
    0.06
    .like
    0.06
    Act Density 0.003%

    No Known Activations