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

    Neuronpedia

    INDEX
    Explanations

    list items and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    现金
    0.51
    取消
    0.44
    不会
    0.40
    异
    0.39
    单独
    0.39
    乖
    0.38
    镰
    0.38
    たつ
    0.38
    琟
    0.38
    江
    0.37
    POSITIVE LOGITS
    ampak
    0.44
    /}
    0.40
     Pich
    0.39
     Sans
    0.38
    BIB
    0.37
    entra
    0.37
    agod
    0.37
     allies
    0.36
     зна
    0.36
     Dand
    0.36
    Act Density 0.000%

    No Known Activations