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

    Neuronpedia

    INDEX
    Explanations

    Rewards

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iken
    -0.06
    ometer
    -0.06
     Indicator
    -0.06
    _contains
    -0.06
    Americans
    -0.06
    	def
    -0.06
    .Adam
    -0.06
     translated
    -0.06
    avirus
    -0.06
    ycop
    -0.06
    POSITIVE LOGITS
     konz
    0.08
     potvr
    0.07
     lips
    0.07
    ér
    0.06
     creation
    0.06
    uestion
    0.06
    隐藏
    0.06
     इन
    0.06
    ุม
    0.06
    ái
    0.06
    Act Density 0.010%

    No Known Activations