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

    Neuronpedia

    INDEX
    Explanations

    paragraph symbol

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	EXPECT
    -0.07
    thers
    -0.07
     TRI
    -0.06
     player
    -0.06
     lending
    -0.06
    aded
    -0.06
     leaning
    -0.06
    ,cp
    -0.06
     elements
    -0.06
     Decay
    -0.06
    POSITIVE LOGITS
     مما
    0.06
     OnPropertyChanged
    0.06
    InOut
    0.06
     월세
    0.06
    observeOn
    0.06
     ملف
    0.06
     ISA
    0.06
    timeofday
    0.06
     отмеч
    0.06
     publishes
    0.06
    Act Density 0.001%

    No Known Activations