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

    Neuronpedia

    INDEX
    Explanations

    but

    np_max-act-logits · gemini-2.0-flashTriggered by @bettyfeng2003
    New Auto-Interp
    Negative Logits
    娆
    -0.08
    ohn
    -0.07
    	buf
    -0.07
    pell
    -0.07
     brisk
    -0.07
    	printk
    -0.07
    باط
    -0.07
    万亩
    -0.07
    乏力
    -0.07
    昺
    -0.07
    POSITIVE LOGITS
     =$
    0.07
     item
    0.07
     zur
    0.07
     related
    0.07
     membership
    0.06
     social
    0.06
    )['
    0.06
    石家
    0.06
    㹦
    0.06
    "]],↵
    0.06
    Act Density 0.050%

    No Known Activations