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

    Neuronpedia

    INDEX
    Explanations

    Chinese text

    np_max-act-logits · gemini-2.0-flashTriggered by @majianfei030706
    New Auto-Interp
    Negative Logits
     AdapterView
    -0.08
    ⚐
    -0.07
    㥄
    -0.07
    ☡
    -0.07
    鸟成长
    -0.07
    𬇕
    -0.07
    	UFUNCTION
    -0.07
    �
    -0.07
     Lecture
    -0.07
    蝘
    -0.07
    POSITIVE LOGITS
    ordinal
    0.07
    性格
    0.07
     Occ
    0.07
    cala
    0.07
     agora
    0.07
    orgh
    0.07
    出具
    0.06
     gn
    0.06
    结果
    0.06
    opyright
    0.06
    Act Density 0.083%

    No Known Activations