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

    Neuronpedia

    INDEX
    Explanations

    hotel fees and policies

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    そこで
    -0.08
    .createStatement
    -0.08
    ここで
    -0.08
    伊斯兰
    -0.08
     estud
    -0.08
     hüküm
    -0.07
    启动仪式
    -0.07
     shortcomings
    -0.07
    -grand
    -0.07
     thí
    -0.07
    POSITIVE LOGITS
    slow
    0.07
    juana
    0.07
    _UUID
    0.07
     treasure
    0.06
    怀疑
    0.06
    	def
    0.06
    _armor
    0.06
    树林
    0.06
     row
    0.06
    _KHR
    0.06
    Act Density 0.009%

    No Known Activations