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

    Neuronpedia

    INDEX
    Explanations

    .datetime

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .indices
    -0.07
    为什么
    -0.07
    Pref
    -0.07
    嘛
    -0.07
    .jsoup
    -0.07
    爷
    -0.07
     جی
    -0.06
    CMD
    -0.06
     Sunny
    -0.06
    	def
    -0.06
    POSITIVE LOGITS
    (en
    0.06
    hor
    0.06
    ')
    0.06
    /s
    0.06
    ’,
    0.06
     exploitation
    0.06
    ELY
    0.06
     khiển
    0.06
    istik
    0.05
     imperative
    0.05
    Act Density 0.004%

    No Known Activations